Retro Diffusion Pixel Art

Official17 toolsLive

by Retro-Diffusion

Generate authentic pixel art - sprites, animations, and tilesets - from any MCP client

Captured live from the server via tools/list.

authenticate

Authenticate this MCP session with a RetroDiffusion public API key.

Parameters1

api_key

string

required

RetroDiffusion API key (rdpk-...), created free at https://retrodiffusion.ai/app/devtools.

Raw schema

{
  "type": "object",
  "properties": {
    "api_key": {
      "description": "RetroDiffusion API key (rdpk-...), created free at https://retrodiffusion.ai/app/devtools.",
      "type": "string"
    }
  },
  "required": [
    "api_key"
  ]
}

logout

Clear the authenticated RetroDiffusion API key for this MCP session.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

create_user_style

Create a user style from the public RD Pro template using /v1/styles. Use `style_reference_images` and `style_reference_caption` for style-level references. These are baked into the custom style and are not the same as per-inference `reference_images`.

Parameters16

name	string	required	Display name for the custom style.
description	any	optional	Short description of the custom style.
style_icon	any	optional	Icon name for the style (e.g. 'sparkles').
reference_images	any	optional	Alias for style_reference_images on this tool; prefer style_reference_images and never provide both.
style_reference_images	any	optional	Style-level reference image(s), base64, baked into the custom style (max 1 via the public API).
reference_caption	any	optional	Alias for style_reference_caption on this tool; prefer style_reference_caption and never provide both.
style_reference_caption	any	optional	Caption describing the style reference image(s).
apply_prompt_fixer	any	optional	Let the API tidy prompts automatically for this style (default true).
llm_instructions	any	optional	Instructions for the prompt-expansion LLM when this style is used.
expanded_llm_instructions	any	optional	Extended instructions for the prompt-expansion LLM.
user_prompt_template	any	optional	Prompt template for the style; must contain the {prompt} token.
force_palette	any	optional	Always apply palette constraining for this style.
force_bg_removal	any	optional	Always remove backgrounds for this style.
min_width	any	optional	Force a fixed width (96-256); must be provided together with min_height.
min_height	any	optional	Force a fixed height (96-256); must be provided together with min_width.
rd_api_key	any	optional	RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "description": "Display name for the custom style.",
      "type": "string"
    },
    "description": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Short description of the custom style."
    },
    "style_icon": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Icon name for the style (e.g. 'sparkles')."
    },
    "reference_images": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Alias for style_reference_images on this tool; prefer style_reference_images and never provide both."
    },
    "style_reference_images": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Style-level reference image(s), base64, baked into the custom style (max 1 via the public API)."
    },
    "reference_caption": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Alias for style_reference_caption on this tool; prefer style_reference_caption and never provide both."
    },
    "style_reference_caption": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Caption describing the style reference image(s)."
    },
    "apply_prompt_fixer": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Let the API tidy prompts automatically for this style (default true)."
    },
    "llm_instructions": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Instructions for the prompt-expansion LLM when this style is used."
    },
    "expanded_llm_instructions": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Extended instructions for the prompt-expansion LLM."
    },
    "user_prompt_template": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Prompt template for the style; must contain the {prompt} token."
    },
    "force_palette": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Always apply palette constraining for this style."
    },
    "force_bg_removal": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Always remove backgrounds for this style."
    },
    "min_width": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Force a fixed width (96-256); must be provided together with min_height."
    },
    "min_height": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Force a fixed height (96-256); must be provided together with min_width."
    },
    "rd_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth."
    }
  },
  "required": [
    "name"
  ]
}

update_user_style

Update a public RD Pro user style using /v1/styles/{style_id}. Use `style_reference_images` and `style_reference_caption` for style-level references. These are baked into the custom style and are not the same as per-inference `reference_images`.

Parameters18

style_id	string	required	Style id — the internal id or the prompt_style/public id (e.g. user__mystyle_ab12).
name	any	optional	New display name for the custom style.
description	any	optional	Short description of the custom style.
style_icon	any	optional	Icon name for the style (e.g. 'sparkles').
reference_images	any	optional	Alias for style_reference_images on this tool; prefer style_reference_images and never provide both.
style_reference_images	any	optional	Style-level reference image(s), base64, baked into the custom style (max 1 via the public API).
reference_caption	any	optional	Alias for style_reference_caption on this tool; prefer style_reference_caption and never provide both.
style_reference_caption	any	optional	Caption describing the style reference image(s).
apply_prompt_fixer	any	optional	Let the API tidy prompts automatically for this style (default true).
llm_instructions	any	optional	Instructions for the prompt-expansion LLM when this style is used.
expanded_llm_instructions	any	optional	Extended instructions for the prompt-expansion LLM.
user_prompt_template	any	optional	Prompt template for the style; must contain the {prompt} token.
force_palette	any	optional	Always apply palette constraining for this style.
force_bg_removal	any	optional	Always remove backgrounds for this style.
min_width	any	optional	Force a fixed width (96-256); must be provided together with min_height.
min_height	any	optional	Force a fixed height (96-256); must be provided together with min_width.
reset_forced_dimensions	boolean	optional	Clear previously forced dimensions; do not combine with min_width/min_height.
rd_api_key	any	optional	RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

Raw schema

{
  "type": "object",
  "properties": {
    "style_id": {
      "description": "Style id — the internal id or the prompt_style/public id (e.g. user__mystyle_ab12).",
      "type": "string"
    },
    "name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "New display name for the custom style."
    },
    "description": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Short description of the custom style."
    },
    "style_icon": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Icon name for the style (e.g. 'sparkles')."
    },
    "reference_images": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Alias for style_reference_images on this tool; prefer style_reference_images and never provide both."
    },
    "style_reference_images": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Style-level reference image(s), base64, baked into the custom style (max 1 via the public API)."
    },
    "reference_caption": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Alias for style_reference_caption on this tool; prefer style_reference_caption and never provide both."
    },
    "style_reference_caption": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Caption describing the style reference image(s)."
    },
    "apply_prompt_fixer": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Let the API tidy prompts automatically for this style (default true)."
    },
    "llm_instructions": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Instructions for the prompt-expansion LLM when this style is used."
    },
    "expanded_llm_instructions": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Extended instructions for the prompt-expansion LLM."
    },
    "user_prompt_template": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Prompt template for the style; must contain the {prompt} token."
    },
    "force_palette": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Always apply palette constraining for this style."
    },
    "force_bg_removal": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Always remove backgrounds for this style."
    },
    "min_width": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Force a fixed width (96-256); must be provided together with min_height."
    },
    "min_height": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Force a fixed height (96-256); must be provided together with min_width."
    },
    "reset_forced_dimensions": {
      "default": false,
      "description": "Clear previously forced dimensions; do not combine with min_width/min_height.",
      "type": "boolean"
    },
    "rd_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth."
    }
  },
  "required": [
    "style_id"
  ]
}

delete_user_style

Delete a user style using /v1/styles/{style_id}. style_id can be either internal id or prompt_style/public_id.

Parameters2

style_id	string	required	Style id — the internal id or the prompt_style/public id (e.g. user__mystyle_ab12).
rd_api_key	any	optional	RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

Raw schema

{
  "type": "object",
  "properties": {
    "style_id": {
      "description": "Style id — the internal id or the prompt_style/public id (e.g. user__mystyle_ab12).",
      "type": "string"
    },
    "rd_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth."
    }
  },
  "required": [
    "style_id"
  ]
}

list_available_styles

List publicly available styles from /v1/styles/selector. Use this to discover valid prompt_style values plus style metadata such as require_input_image and supports_reference_images.

Parameters3

model	any	optional	Filter styles by model: rd_fast, rd_plus, rd_pro, or rd_mini.
tab	any	optional	Filter styles by tab: tab:image, tab:animation, tab:advanced-animation, or tab:tileset.
rd_api_key	any	optional	RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

Raw schema

{
  "type": "object",
  "properties": {
    "model": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Filter styles by model: rd_fast, rd_plus, rd_pro, or rd_mini."
    },
    "tab": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Filter styles by tab: tab:image, tab:animation, tab:advanced-animation, or tab:tileset."
    },
    "rd_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth."
    }
  }
}

list_available_models

Return unique public model identifiers available in /v1/styles/selector.

Parameters1

rd_api_key

any

optional

RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

Raw schema

{
  "type": "object",
  "properties": {
    "rd_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth."
    }
  }
}

get_style_usage

Explain how to use a public prompt_style from the RetroDiffusion API. Use this before create_inference if you are unsure whether a style expects `input_image`, supports per-inference `reference_images`, or whether you meant style-level `style_reference_images`.

Parameters2

prompt_style	string	required	Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style).
rd_api_key	any	optional	RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

Raw schema

{
  "type": "object",
  "properties": {
    "prompt_style": {
      "description": "Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style).",
      "type": "string"
    },
    "rd_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth."
    }
  },
  "required": [
    "prompt_style"
  ]
}

get_balance

Get credits/balance using the public /v1/inferences/credits endpoint.

Parameters1

rd_api_key

any

optional

RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

Raw schema

{
  "type": "object",
  "properties": {
    "rd_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth."
    }
  }
}

estimate_inference_cost

Estimate generation cost using the public /v1/inferences endpoint with check_cost=true. Use `input_image` for the main source image, `reference_images` for extra per-inference guidance, and `style_reference_images` only on create_user_style/update_user_style.

Parameters20

prompt	string	required	Describe the SUBJECT only (e.g. 'a knight resting by a campfire'). Never write 'pixel art' — the selected style handles all rendering.
prompt_style	string	required	Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style).
width	integer	required	Output width in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.
height	integer	required	Output height in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.
num_images	integer	optional	How many images to generate in one batch. Style-specific maximums apply.
input_image	any	optional	Base64 PNG used as the main source image for edits, variations, tilesets, animations, or styles that require a starting frame. Raw base64 or a data URL.
reference_images	any	optional	Extra per-inference guidance images (base64), only for styles where supports_reference_images is true. Not for defining custom styles.
extra_input_image	any	optional	Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced).
input_palette	any	optional	Base64 image of a color palette; output colors are constrained to it.
strength	any	optional	How strongly to change input_image, 0-1 (default 0.75). Lower values keep more of the original.
extra_prompt	any	optional	Secondary prompt for styles that use one (e.g. the transition texture in advanced tilesets).
frames_duration	any	optional	Animation frame count for animation styles: 4, 6, 8, 10, 12, or 16.
return_spritesheet	any	optional	For animation styles: return a PNG sprite sheet instead of a GIF.
return_pre_palette	any	optional	Also return the render from before palette constraints were applied.
return_non_bg_removed	any	optional	Also return the render from before background removal was applied.
bypass_prompt_expansion	any	optional	Skip the automatic LLM prompt enrichment and use the prompt verbatim.
include_downloadable_data	any	optional	Include extra structured assets when available (e.g. tileset atlas JSON, animation frame data).
upscale_output_factor	any	optional	Integer upscale factor for the output image; 1 returns the native pixel size.
timeout_seconds	any	optional	Read-timeout override in seconds for this call; increase for animations or large batches.
rd_api_key	any	optional	RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

Raw schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "description": "Describe the SUBJECT only (e.g. 'a knight resting by a campfire'). Never write 'pixel art' — the selected style handles all rendering.",
      "type": "string"
    },
    "prompt_style": {
      "description": "Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style).",
      "type": "string"
    },
    "width": {
      "description": "Output width in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.",
      "type": "integer"
    },
    "height": {
      "description": "Output height in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.",
      "type": "integer"
    },
    "num_images": {
      "default": 1,
      "description": "How many images to generate in one batch. Style-specific maximums apply.",
      "type": "integer"
    },
    "input_image": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Base64 PNG used as the main source image for edits, variations, tilesets, animations, or styles that require a starting frame. Raw base64 or a data URL."
    },
    "reference_images": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Extra per-inference guidance images (base64), only for styles where supports_reference_images is true. Not for defining custom styles."
    },
    "extra_input_image": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced)."
    },
    "input_palette": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Base64 image of a color palette; output colors are constrained to it."
    },
    "strength": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "How strongly to change input_image, 0-1 (default 0.75). Lower values keep more of the original."
    },
    "extra_prompt": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Secondary prompt for styles that use one (e.g. the transition texture in advanced tilesets)."
    },
    "frames_duration": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Animation frame count for animation styles: 4, 6, 8, 10, 12, or 16."
    },
    "return_spritesheet": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "For animation styles: return a PNG sprite sheet instead of a GIF."
    },
    "return_pre_palette": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Also return the render from before palette constraints were applied."
    },
    "return_non_bg_removed": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Also return the render from before background removal was applied."
    },
    "bypass_prompt_expansion": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Skip the automatic LLM prompt enrichment and use the prompt verbatim."
    },
    "include_downloadable_data": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Include extra structured assets when available (e.g. tileset atlas JSON, animation frame data)."
    },
    "upscale_output_factor": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Integer upscale factor for the output image; 1 returns the native pixel size."
    },
    "timeout_seconds": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Read-timeout override in seconds for this call; increase for animations or large batches."
    },
    "rd_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth."
    }
  },
  "required": [
    "prompt",
    "prompt_style",
    "width",
    "height"
  ]
}

create_inference

Generate images using the public /v1/inferences endpoint. For the highest quality prefer RD Pro styles (rd_pro__*); they support reference_images for character/style consistency. For animation styles prefer start_inference_job + get_inference_job instead — animations are long-running. Use `input_image` for the main source image, `reference_images` for extra per-inference guidance, and `style_reference_images` only on create_user_style/update_user_style. The response excludes raw base64 image payloads to keep MCP outputs compact.

Parameters25

prompt	string	required	Describe the SUBJECT only (e.g. 'a knight resting by a campfire'). Never write 'pixel art' — the selected style handles all rendering.
prompt_style	string	required	Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style).
width	integer	required	Output width in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.
height	integer	required	Output height in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.
num_images	integer	optional	How many images to generate in one batch. Style-specific maximums apply.
input_image	any	optional	Base64 PNG used as the main source image for edits, variations, tilesets, animations, or styles that require a starting frame. Raw base64 or a data URL.
reference_images	any	optional	Extra per-inference guidance images (base64), only for styles where supports_reference_images is true. Not for defining custom styles.
extra_input_image	any	optional	Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced).
input_palette	any	optional	Base64 image of a color palette; output colors are constrained to it.
strength	any	optional	How strongly to change input_image, 0-1 (default 0.75). Lower values keep more of the original.
extra_prompt	any	optional	Secondary prompt for styles that use one (e.g. the transition texture in advanced tilesets).
frames_duration	any	optional	Animation frame count for animation styles: 4, 6, 8, 10, 12, or 16.
return_spritesheet	any	optional	For animation styles: return a PNG sprite sheet instead of a GIF.
return_pre_palette	any	optional	Also return the render from before palette constraints were applied.
return_non_bg_removed	any	optional	Also return the render from before background removal was applied.
bypass_prompt_expansion	any	optional	Skip the automatic LLM prompt enrichment and use the prompt verbatim.
include_downloadable_data	any	optional	Include extra structured assets when available (e.g. tileset atlas JSON, animation frame data).
upscale_output_factor	any	optional	Integer upscale factor for the output image; 1 returns the native pixel size.
seed	any	optional	Seed for reproducible results; reuse the same seed to iterate on one composition.
remove_bg	boolean	optional	Remove the background for transparent output.
tile_x	boolean	optional	Make the result tile seamlessly on the horizontal axis.
tile_y	boolean	optional	Make the result tile seamlessly on the vertical axis.
upload_outputs	boolean	optional	Host outputs and return URLs in output_urls (recommended for MCP clients) instead of only base64 payloads.
timeout_seconds	any	optional	Read-timeout override in seconds for this call; increase for animations or large batches.
rd_api_key	any	optional	RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

Raw schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "description": "Describe the SUBJECT only (e.g. 'a knight resting by a campfire'). Never write 'pixel art' — the selected style handles all rendering.",
      "type": "string"
    },
    "prompt_style": {
      "description": "Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style).",
      "type": "string"
    },
    "width": {
      "description": "Output width in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.",
      "type": "integer"
    },
    "height": {
      "description": "Output height in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.",
      "type": "integer"
    },
    "num_images": {
      "default": 1,
      "description": "How many images to generate in one batch. Style-specific maximums apply.",
      "type": "integer"
    },
    "input_image": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Base64 PNG used as the main source image for edits, variations, tilesets, animations, or styles that require a starting frame. Raw base64 or a data URL."
    },
    "reference_images": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Extra per-inference guidance images (base64), only for styles where supports_reference_images is true. Not for defining custom styles."
    },
    "extra_input_image": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced)."
    },
    "input_palette": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Base64 image of a color palette; output colors are constrained to it."
    },
    "strength": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "How strongly to change input_image, 0-1 (default 0.75). Lower values keep more of the original."
    },
    "extra_prompt": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Secondary prompt for styles that use one (e.g. the transition texture in advanced tilesets)."
    },
    "frames_duration": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Animation frame count for animation styles: 4, 6, 8, 10, 12, or 16."
    },
    "return_spritesheet": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "For animation styles: return a PNG sprite sheet instead of a GIF."
    },
    "return_pre_palette": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Also return the render from before palette constraints were applied."
    },
    "return_non_bg_removed": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Also return the render from before background removal was applied."
    },
    "bypass_prompt_expansion": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Skip the automatic LLM prompt enrichment and use the prompt verbatim."
    },
    "include_downloadable_data": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Include extra structured assets when available (e.g. tileset atlas JSON, animation frame data)."
    },
    "upscale_output_factor": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Integer upscale factor for the output image; 1 returns the native pixel size."
    },
    "seed": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Seed for reproducible results; reuse the same seed to iterate on one composition."
    },
    "remove_bg": {
      "default": false,
      "description": "Remove the background for transparent output.",
      "type": "boolean"
    },
    "tile_x": {
      "default": false,
      "description": "Make the result tile seamlessly on the horizontal axis.",
      "type": "boolean"
    },
    "tile_y": {
      "default": false,
      "description": "Make the result tile seamlessly on the vertical axis.",
      "type": "boolean"
    },
    "upload_outputs": {
      "default": true,
      "description": "Host outputs and return URLs in output_urls (recommended for MCP clients) instead of only base64 payloads.",
      "type": "boolean"
    },
    "timeout_seconds": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Read-timeout override in seconds for this call; increase for animations or large batches."
    },
    "rd_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth."
    }
  },
  "required": [
    "prompt",
    "prompt_style",
    "width",
    "height"
  ]
}

list_edit_tools

List the enabled canvas edit tools from /v1/edit/tools with their fields, costs, and limits. Edit tools are the recommended way to post-process generated pixel art: background removal, palette conversion, color reduction, pixel correction, rotation, inpainting, outpainting, seam tiling, and prompt-driven edits.

Parameters1

rd_api_key

any

optional

RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

Raw schema

{
  "type": "object",
  "properties": {
    "rd_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth."
    }
  }
}

run_edit_tool

Run a canvas edit tool on an image via /v1/edit/tools/{tool_id}. Free tools: color_reducer, palette_converter, pixel_correction, k_centroid_downscale, rotate. $0.01 tools: background_remover, color_style_transfer. Premium ($0.18): image_edit, inpainting, outpainting, seam_tiling. Use estimate_edit_tool_cost first for anything that charges — estimation is free. The edited image is returned in base64_images.

Parameters26

tool_id	string	required	Edit tool id. One of: image_edit, inpainting, outpainting, seam_tiling, background_remover, color_style_transfer, color_reducer, palette_converter, pixel_correction, k_centroid_downscale, rotate. Use list_edit_tools for authoritative fields, costs, and limits.
input_image	string	required	Base64 PNG of the image to edit (raw base64 or a data URL). Required by every edit tool.
prompt	any	optional	What to generate or change (required by image_edit and inpainting; optional for outpainting).
mask_image	any	optional	Base64 mask for inpainting: white pixels are regenerated, black pixels are kept.
extra_input_image	any	optional	Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced).
input_palette	any	optional	Base64 image of a color palette; output colors are constrained to it.
expand_left	any	optional	Outpainting: pixels to add on the left edge.
expand_right	any	optional	Outpainting: pixels to add on the right edge.
expand_top	any	optional	Outpainting: pixels to add on the top edge.
expand_bottom	any	optional	Outpainting: pixels to add on the bottom edge.
soft_inpaint	any	optional	Inpainting/outpainting: blend edits softly with the surrounding pixels.
tile_x	any	optional	seam_tiling: repair the horizontal seam (tool default applies when omitted).
tile_y	any	optional	seam_tiling: repair the vertical seam (tool default applies when omitted).
seam_width	any	optional	seam_tiling: width in pixels of the seam band to repair.
repair_window_size	any	optional	seam_tiling: size of the repair window.
color_count	any	optional	color_reducer: target number of colors.
dither_mode	any	optional	color_reducer/palette_converter: dithering mode.
dither_strength	any	optional	color_reducer/palette_converter: dithering strength.
width	any	optional	k_centroid_downscale: target width in pixels (required for that tool).
height	any	optional	k_centroid_downscale: target height in pixels (required for that tool).
rotation_degrees	any	optional	rotate: rotation angle in degrees (clean-edge pixel rotation).
transparency_threshold	any	optional	background_remover: alpha threshold for treating pixels as transparent.
force_solid_pixels	any	optional	background_remover: force fully solid or fully transparent pixels (tool default applies when omitted).
seed	any	optional	Seed for reproducible results; reuse the same seed to iterate on one composition.
timeout_seconds	any	optional	Read-timeout override in seconds for this call; increase for animations or large batches.
rd_api_key	any	optional	RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

Raw schema

{
  "type": "object",
  "properties": {
    "tool_id": {
      "description": "Edit tool id. One of: image_edit, inpainting, outpainting, seam_tiling, background_remover, color_style_transfer, color_reducer, palette_converter, pixel_correction, k_centroid_downscale, rotate. Use list_edit_tools for authoritative fields, costs, and limits.",
      "type": "string"
    },
    "input_image": {
      "description": "Base64 PNG of the image to edit (raw base64 or a data URL). Required by every edit tool.",
      "type": "string"
    },
    "prompt": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "What to generate or change (required by image_edit and inpainting; optional for outpainting)."
    },
    "mask_image": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Base64 mask for inpainting: white pixels are regenerated, black pixels are kept."
    },
    "extra_input_image": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced)."
    },
    "input_palette": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Base64 image of a color palette; output colors are constrained to it."
    },
    "expand_left": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Outpainting: pixels to add on the left edge."
    },
    "expand_right": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Outpainting: pixels to add on the right edge."
    },
    "expand_top": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Outpainting: pixels to add on the top edge."
    },
    "expand_bottom": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Outpainting: pixels to add on the bottom edge."
    },
    "soft_inpaint": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Inpainting/outpainting: blend edits softly with the surrounding pixels."
    },
    "tile_x": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "seam_tiling: repair the horizontal seam (tool default applies when omitted)."
    },
    "tile_y": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "seam_tiling: repair the vertical seam (tool default applies when omitted)."
    },
    "seam_width": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "seam_tiling: width in pixels of the seam band to repair."
    },
    "repair_window_size": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "seam_tiling: size of the repair window."
    },
    "color_count": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "color_reducer: target number of colors."
    },
    "dither_mode": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "color_reducer/palette_converter: dithering mode."
    },
    "dither_strength": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "color_reducer/palette_converter: dithering strength."
    },
    "width": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "k_centroid_downscale: target width in pixels (required for that tool)."
    },
    "height": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "k_centroid_downscale: target height in pixels (required for that tool)."
    },
    "rotation_degrees": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "rotate: rotation angle in degrees (clean-edge pixel rotation)."
    },
    "transparency_threshold": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "background_remover: alpha threshold for treating pixels as transparent."
    },
    "force_solid_pixels": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "background_remover: force fully solid or fully transparent pixels (tool default applies when omitted)."
    },
    "seed": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Seed for reproducible results; reuse the same seed to iterate on one composition."
    },
    "timeout_seconds": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Read-timeout override in seconds for this call; increase for animations or large batches."
    },
    "rd_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth."
    }
  },
  "required": [
    "tool_id",
    "input_image"
  ]
}

estimate_edit_tool_cost

Validate an edit-tool request and estimate its cost and duration without running it. Always free.

Parameters25

tool_id	string	required	Edit tool id. One of: image_edit, inpainting, outpainting, seam_tiling, background_remover, color_style_transfer, color_reducer, palette_converter, pixel_correction, k_centroid_downscale, rotate. Use list_edit_tools for authoritative fields, costs, and limits.
input_image	string	required	Base64 PNG of the image to edit (raw base64 or a data URL). Required by every edit tool.
prompt	any	optional	What to generate or change (required by image_edit and inpainting; optional for outpainting).
mask_image	any	optional	Base64 mask for inpainting: white pixels are regenerated, black pixels are kept.
extra_input_image	any	optional	Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced).
input_palette	any	optional	Base64 image of a color palette; output colors are constrained to it.
expand_left	any	optional	Outpainting: pixels to add on the left edge.
expand_right	any	optional	Outpainting: pixels to add on the right edge.
expand_top	any	optional	Outpainting: pixels to add on the top edge.
expand_bottom	any	optional	Outpainting: pixels to add on the bottom edge.
soft_inpaint	any	optional	Inpainting/outpainting: blend edits softly with the surrounding pixels.
tile_x	any	optional	seam_tiling: repair the horizontal seam (tool default applies when omitted).
tile_y	any	optional	seam_tiling: repair the vertical seam (tool default applies when omitted).
seam_width	any	optional	seam_tiling: width in pixels of the seam band to repair.
repair_window_size	any	optional	seam_tiling: size of the repair window.
color_count	any	optional	color_reducer: target number of colors.
dither_mode	any	optional	color_reducer/palette_converter: dithering mode.
dither_strength	any	optional	color_reducer/palette_converter: dithering strength.
width	any	optional	k_centroid_downscale: target width in pixels (required for that tool).
height	any	optional	k_centroid_downscale: target height in pixels (required for that tool).
rotation_degrees	any	optional	rotate: rotation angle in degrees (clean-edge pixel rotation).
transparency_threshold	any	optional	background_remover: alpha threshold for treating pixels as transparent.
force_solid_pixels	any	optional	background_remover: force fully solid or fully transparent pixels (tool default applies when omitted).
timeout_seconds	any	optional	Read-timeout override in seconds for this call; increase for animations or large batches.
rd_api_key	any	optional	RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

Raw schema

{
  "type": "object",
  "properties": {
    "tool_id": {
      "description": "Edit tool id. One of: image_edit, inpainting, outpainting, seam_tiling, background_remover, color_style_transfer, color_reducer, palette_converter, pixel_correction, k_centroid_downscale, rotate. Use list_edit_tools for authoritative fields, costs, and limits.",
      "type": "string"
    },
    "input_image": {
      "description": "Base64 PNG of the image to edit (raw base64 or a data URL). Required by every edit tool.",
      "type": "string"
    },
    "prompt": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "What to generate or change (required by image_edit and inpainting; optional for outpainting)."
    },
    "mask_image": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Base64 mask for inpainting: white pixels are regenerated, black pixels are kept."
    },
    "extra_input_image": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced)."
    },
    "input_palette": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Base64 image of a color palette; output colors are constrained to it."
    },
    "expand_left": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Outpainting: pixels to add on the left edge."
    },
    "expand_right": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Outpainting: pixels to add on the right edge."
    },
    "expand_top": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Outpainting: pixels to add on the top edge."
    },
    "expand_bottom": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Outpainting: pixels to add on the bottom edge."
    },
    "soft_inpaint": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Inpainting/outpainting: blend edits softly with the surrounding pixels."
    },
    "tile_x": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "seam_tiling: repair the horizontal seam (tool default applies when omitted)."
    },
    "tile_y": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "seam_tiling: repair the vertical seam (tool default applies when omitted)."
    },
    "seam_width": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "seam_tiling: width in pixels of the seam band to repair."
    },
    "repair_window_size": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "seam_tiling: size of the repair window."
    },
    "color_count": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "color_reducer: target number of colors."
    },
    "dither_mode": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "color_reducer/palette_converter: dithering mode."
    },
    "dither_strength": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "color_reducer/palette_converter: dithering strength."
    },
    "width": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "k_centroid_downscale: target width in pixels (required for that tool)."
    },
    "height": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "k_centroid_downscale: target height in pixels (required for that tool)."
    },
    "rotation_degrees": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "rotate: rotation angle in degrees (clean-edge pixel rotation)."
    },
    "transparency_threshold": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "background_remover: alpha threshold for treating pixels as transparent."
    },
    "force_solid_pixels": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "background_remover: force fully solid or fully transparent pixels (tool default applies when omitted)."
    },
    "timeout_seconds": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Read-timeout override in seconds for this call; increase for animations or large batches."
    },
    "rd_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth."
    }
  },
  "required": [
    "tool_id",
    "input_image"
  ]
}

start_inference_job

Start a generation as an async job (POST /v1/inferences with async=true) and return a task_id. Recommended for advanced animations (rd_advanced_animation__*), other animation styles, and batches — they run for tens of seconds and can outlive a synchronous MCP call. Poll the returned task_id with get_inference_job roughly every 2-5 seconds.

Parameters25

prompt	string	required	Describe the SUBJECT only (e.g. 'a knight resting by a campfire'). Never write 'pixel art' — the selected style handles all rendering.
prompt_style	string	required	Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style).
width	integer	required	Output width in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.
height	integer	required	Output height in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.
num_images	integer	optional	How many images to generate in one batch. Style-specific maximums apply.
input_image	any	optional	Base64 PNG used as the main source image for edits, variations, tilesets, animations, or styles that require a starting frame. Raw base64 or a data URL.
reference_images	any	optional	Extra per-inference guidance images (base64), only for styles where supports_reference_images is true. Not for defining custom styles.
extra_input_image	any	optional	Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced).
input_palette	any	optional	Base64 image of a color palette; output colors are constrained to it.
strength	any	optional	How strongly to change input_image, 0-1 (default 0.75). Lower values keep more of the original.
extra_prompt	any	optional	Secondary prompt for styles that use one (e.g. the transition texture in advanced tilesets).
frames_duration	any	optional	Animation frame count for animation styles: 4, 6, 8, 10, 12, or 16.
return_spritesheet	any	optional	For animation styles: return a PNG sprite sheet instead of a GIF.
return_pre_palette	any	optional	Also return the render from before palette constraints were applied.
return_non_bg_removed	any	optional	Also return the render from before background removal was applied.
bypass_prompt_expansion	any	optional	Skip the automatic LLM prompt enrichment and use the prompt verbatim.
include_downloadable_data	any	optional	Include extra structured assets when available (e.g. tileset atlas JSON, animation frame data).
upscale_output_factor	any	optional	Integer upscale factor for the output image; 1 returns the native pixel size.
seed	any	optional	Seed for reproducible results; reuse the same seed to iterate on one composition.
remove_bg	boolean	optional	Remove the background for transparent output.
tile_x	boolean	optional	Make the result tile seamlessly on the horizontal axis.
tile_y	boolean	optional	Make the result tile seamlessly on the vertical axis.
upload_outputs	boolean	optional	Host outputs and return URLs in output_urls (recommended for MCP clients) instead of only base64 payloads.
timeout_seconds	any	optional	Read-timeout override in seconds for this call; increase for animations or large batches.
rd_api_key	any	optional	RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

Raw schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "description": "Describe the SUBJECT only (e.g. 'a knight resting by a campfire'). Never write 'pixel art' — the selected style handles all rendering.",
      "type": "string"
    },
    "prompt_style": {
      "description": "Style id from list_available_styles (e.g. 'rd_fast__default', 'rd_pro__isometric', or a custom 'user__...' style).",
      "type": "string"
    },
    "width": {
      "description": "Output width in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.",
      "type": "integer"
    },
    "height": {
      "description": "Output height in pixels. Each style enforces its own limits; check list_available_styles or get_style_usage.",
      "type": "integer"
    },
    "num_images": {
      "default": 1,
      "description": "How many images to generate in one batch. Style-specific maximums apply.",
      "type": "integer"
    },
    "input_image": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Base64 PNG used as the main source image for edits, variations, tilesets, animations, or styles that require a starting frame. Raw base64 or a data URL."
    },
    "reference_images": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Extra per-inference guidance images (base64), only for styles where supports_reference_images is true. Not for defining custom styles."
    },
    "extra_input_image": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Second base64 input image for styles that use one (e.g. the second texture in rd_tile__tileset_advanced)."
    },
    "input_palette": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Base64 image of a color palette; output colors are constrained to it."
    },
    "strength": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "How strongly to change input_image, 0-1 (default 0.75). Lower values keep more of the original."
    },
    "extra_prompt": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Secondary prompt for styles that use one (e.g. the transition texture in advanced tilesets)."
    },
    "frames_duration": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Animation frame count for animation styles: 4, 6, 8, 10, 12, or 16."
    },
    "return_spritesheet": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "For animation styles: return a PNG sprite sheet instead of a GIF."
    },
    "return_pre_palette": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Also return the render from before palette constraints were applied."
    },
    "return_non_bg_removed": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Also return the render from before background removal was applied."
    },
    "bypass_prompt_expansion": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Skip the automatic LLM prompt enrichment and use the prompt verbatim."
    },
    "include_downloadable_data": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Include extra structured assets when available (e.g. tileset atlas JSON, animation frame data)."
    },
    "upscale_output_factor": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Integer upscale factor for the output image; 1 returns the native pixel size."
    },
    "seed": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Seed for reproducible results; reuse the same seed to iterate on one composition."
    },
    "remove_bg": {
      "default": false,
      "description": "Remove the background for transparent output.",
      "type": "boolean"
    },
    "tile_x": {
      "default": false,
      "description": "Make the result tile seamlessly on the horizontal axis.",
      "type": "boolean"
    },
    "tile_y": {
      "default": false,
      "description": "Make the result tile seamlessly on the vertical axis.",
      "type": "boolean"
    },
    "upload_outputs": {
      "default": true,
      "description": "Host outputs and return URLs in output_urls (recommended for MCP clients) instead of only base64 payloads.",
      "type": "boolean"
    },
    "timeout_seconds": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Read-timeout override in seconds for this call; increase for animations or large batches."
    },
    "rd_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth."
    }
  },
  "required": [
    "prompt",
    "prompt_style",
    "width",
    "height"
  ]
}

get_inference_job

Check the status of an async generation started with start_inference_job. Statuses: pending, running, succeeded, failed. On success the result carries hosted output_urls (raw base64 payloads are excluded to keep MCP outputs compact).

Parameters2

task_id	string	required	Async job id returned by start_inference_job.
rd_api_key	any	optional	RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth.

Raw schema

{
  "type": "object",
  "properties": {
    "task_id": {
      "description": "Async job id returned by start_inference_job.",
      "type": "string"
    },
    "rd_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "RetroDiffusion API key (rdpk-...) for this call only; overrides session or header auth."
    }
  },
  "required": [
    "task_id"
  ]
}

get_service_status

Check RetroDiffusion subsystem health (/v1/status, no auth). Useful before bulk generation runs.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

README.md8 KBView on GitHub

Retro Diffusion

Retro Diffusion MCP Server

Generate real pixel art — sprites, characters, animations, and tilesets — from any MCP-capable AI assistant.
Grid-aligned pixels, controlled palettes, transparent backgrounds. Not "pixel-art style" images. The real thing.

Website · API Docs · API Examples · Discord

MIT License Streamable HTTP

This is a hosted, remote MCP server — nothing to install or run locally. Point your client at the endpoint, add your API key, and your assistant can browse 90+ pixel art styles, estimate costs for free, and generate game-ready art.

code

Endpoint:  https://mcp.retrodiffusion.ai/mcp     (Streamable HTTP)
Auth:      Authorization: Bearer <your API key>   (keys start with rdpk-)

Get an API key (2 minutes)

Create a free account at retrodiffusion.ai — new accounts include free starter credits.
Open Developer Tools and click Create API Key.

Pricing is pay-per-generation (from ~$0.01 per image), prepaid, no subscription, and credits never expire. Cost estimation is always free, so your agent can check the price of anything before spending.

Setup by client

Claude Code

bash

claude mcp add --transport http retro-diffusion https://mcp.retrodiffusion.ai/mcp \
  --header "Authorization: Bearer rdpk-YOUR-KEY"

Or install the plugin (bundles the server plus a pixel-art workflow skill):

code

/plugin marketplace add Retro-Diffusion/retro-diffusion-mcp
/plugin install pixel-art@retro-diffusion

Cursor

Click the Add to Cursor badge above, then replace YOUR_API_KEY — or add to ~/.cursor/mcp.json:

json

{
  "mcpServers": {
    "retro-diffusion": {
      "url": "https://mcp.retrodiffusion.ai/mcp",
      "headers": { "Authorization": "Bearer rdpk-YOUR-KEY" }
    }
  }
}

VS Code (GitHub Copilot)

Add to mcp.json (Command Palette → "MCP: Add Server" → HTTP):

json

{
  "servers": {
    "retro-diffusion": {
      "type": "http",
      "url": "https://mcp.retrodiffusion.ai/mcp",
      "headers": { "Authorization": "Bearer rdpk-YOUR-KEY" }
    }
  }
}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

json

{
  "mcpServers": {
    "retro-diffusion": {
      "serverUrl": "https://mcp.retrodiffusion.ai/mcp",
      "headers": { "Authorization": "Bearer rdpk-YOUR-KEY" }
    }
  }
}

Claude Desktop

Use mcp-remote in claude_desktop_config.json:

json

{
  "mcpServers": {
    "retro-diffusion": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://mcp.retrodiffusion.ai/mcp",
        "--header",
        "Authorization: Bearer rdpk-YOUR-KEY"
      ]
    }
  }
}

Anything else

Any MCP client that speaks Streamable HTTP works: URL https://mcp.retrodiffusion.ai/mcp, header Authorization: Bearer rdpk-YOUR-KEY.

Tools

Generate

Tool	What it does
`create_inference`	Generate images, animations (GIF/sprite sheet), or tilesets. Prefer RD Pro styles for top quality
`start_inference_job`	Start generation as an async job — recommended for animations and batches
`get_inference_job`	Poll an async job for status and results
`estimate_inference_cost`	Free price check for any generation before running it

Edit — post-process any image

Tool	What it does
`list_edit_tools`	Enabled edit tools with their fields, costs, and limits
`run_edit_tool`	Run an edit tool: background remover, palette converter, color reducer, pixel correction, rotation, K-centroid downscale (free–$0.01) · image edit, inpainting, outpainting, seam tiling (premium)
`estimate_edit_tool_cost`	Free cost/duration estimate for any edit

Styles

Tool	What it does
`list_available_styles`	Live style catalog with per-style size limits and capabilities
`list_available_models`	The model families: RD Fast, RD Plus, RD Pro, RD Mini
`get_style_usage`	Usage guidance and constraints for a specific style
`create_user_style`	Create a custom style from a reference image (RD Pro template)
`update_user_style`	Modify one of your custom styles
`delete_user_style`	Remove one of your custom styles

Account

Tool	What it does
`authenticate`	Validate an API key and attach it to the session
`get_balance`	Check remaining prepaid balance and credits
`get_service_status`	Subsystem health check (no auth required)
`logout`	Clear the stored session key

What you can make

Sprites & characters — 90+ styles: portraits, game assets, isometric, top-down, platformer, 1-bit, Minecraft items/textures, UI elements, item sheets, character turnarounds
Animations — walk/idle/jump/crouch/attack cycles from a start frame, four-angle walk cycles, 8-direction rotations, VFX, battle sprites; GIF or sprite-sheet output
Tilesets — Wang/blob tilesets, tile variations, single tiles, scene objects
Consistent characters — generate once with RD Pro, then pass the output as a reference image in follow-up generations (up to 9 references)
Edits — img2img, seamless tiling, transparent backgrounds, palette-constrained output

Example prompts to try once connected:

"List the available pixel art styles for animations, then estimate what a 64×64 walking animation would cost."

"Generate a 128×128 pixel art knight resting by a campfire, RD Pro default style, transparent background."

"Create a 16×16 Wang tileset: grey stone path tiles blending into lush grass."

Prompting tips (important)

Describe the subject only — never write "pixel art" in the prompt; the style handles the rendering.
Sizes run 16×16 to 384×384 depending on style; list_available_styles gives exact per-style limits.
Costs range from ~$0.015 (RD Fast) to $0.18/image (RD Pro); animations $0.07–$0.25; tilesets $0.10. estimate_inference_cost is always free — use it first.
Reuse a seed to iterate on the same composition while changing only the prompt.

Who makes this

Retro Diffusion is built by Astropulse — a pixel artist with seven years of freelance experience before building the tool — and is used in production by studios and platforms including Replicate, Poe (Quora), and Scenario. It's designed by artists and held to artist-grade quality standards.

Support

Discord community — fastest answers, the founder is active daily
Full API reference and runnable examples
Service status (no auth required)

License

The contents of this repository (documentation and manifests) are MIT licensed. The Retro Diffusion service itself is governed by its Terms of Service.

Install

Tools (17)

authenticatelogoutcreate_user_styleupdate_user_styledelete_user_stylelist_available_styleslist_available_modelsget_style_usage

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://mcp.retrodiffusion.ai/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "pixel-art": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.retrodiffusion.ai/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.