Image

CCSR

Credit-based pricing. Supports reference images.

Try CCSR →Compare models

Output

image

Inputs

Reference image (required)

Example prompt

Upload any photo — CCSR preserves content consistency while recovering high-frequency texture detail.

Try this prompt →

LLM-ready

API & LLM schema

Exact request contract for this model. Agents can fetch it from /api/v1/models?id=fal-ai/ccsr.

POST/api/v1/generate20 fields · 2 required

Field	Type	Requirement	Contract
`model_id`	constant	Required	ArtEmotion model identifier.
`extra`	object	Optional	Model-specific settings may also be nested here.
`max_credits`	number	Optional	Reject before submission if the estimated list price exceeds this cap. · Range: 1–…
`webhook_url`	string	Optional	Format: uri
`webhook_secret`	string	Optional	Optional model input.
`folder_id`	string	Optional	Optional model input.
`prompt`	string	Optional	Optional model input.
`t_max`	number	Optional	The ending point of uniform sampling strategy. · Default: 0.6667 · Range: 0–1
`tile_diffusion`	string	Optional	If specified, a patch-based sampling strategy will be used for sampling. · Allowed: none, mix, gaussian · Default: none
`color_fix_type`	string	Optional	Type of color correction for samples. · Allowed: none, wavelet, adain · Default: adain
`tile_diffusion_stride`	number	Optional	Stride of sliding patch. · Default: 512 · Range: 128–1024
`tile_vae_encoder_size`	number	Optional	Size of latent image · Default: 1024 · Range: 128–2048
`tile_vae`	boolean	Optional	If specified, a patch-based sampling strategy will be used for VAE decoding. · Default: false
`steps`	number	Optional	The number of steps to run the model for. The higher the number the better the quality and longer it will take to generate. · Default: 50 · Range: 10–100
`t_min`	number	Optional	The starting point of uniform sampling strategy. · Default: 0.3333 · Range: 0–1
`scale`	number	Optional	The scale of the output image. The higher the scale, the bigger the output image will be. · Default: 2 · Range: 1–4
`tile_diffusion_size`	number	Optional	Size of patch. · Default: 1024 · Range: 256–2048
`seed`	integer	Optional	Seed for reproducibility. Different seeds will make slightly different results.
`tile_vae_decoder_size`	number	Optional	Size of VAE patch. · Default: 226 · Range: 64–2048
`reference_image_url`	string	Required	Format: uri

Minimal request example

{
  "model_id": "fal-ai/ccsr",
  "reference_image_url": "https://example.com/reference_image"
}

Raw JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://www.artemotion.ai/api/v1/models?id=fal-ai%2Fccsr",
  "title": "CCSR generation request",
  "description": "Request body accepted by POST /api/v1/generate for fal-ai/ccsr.",
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string",
      "const": "fal-ai/ccsr",
      "description": "ArtEmotion model identifier."
    },
    "extra": {
      "type": "object",
      "additionalProperties": true,
      "description": "Model-specific settings may also be nested here."
    },
    "max_credits": {
      "type": "number",
      "minimum": 1,
      "description": "Reject before submission if the estimated list price exceeds this cap."
    },
    "webhook_url": {
      "type": "string",
      "format": "uri",
      "maxLength": 2048
    },
    "webhook_secret": {
      "type": "string",
      "maxLength": 512
    },
    "folder_id": {
      "type": "string"
    },
    "prompt": {
      "type": "string"
    },
    "t_max": {
      "title": "T Max",
      "description": "The ending point of uniform sampling strategy.",
      "default": 0.6667,
      "type": "number",
      "minimum": 0,
      "maximum": 1
    },
    "tile_diffusion": {
      "title": "Tile Diffusion",
      "description": "If specified, a patch-based sampling strategy will be used for sampling.",
      "default": "none",
      "type": "string",
      "enum": [
        "none",
        "mix",
        "gaussian"
      ]
    },
    "color_fix_type": {
      "title": "Color Fix Type",
      "description": "Type of color correction for samples.",
      "default": "adain",
      "type": "string",
      "enum": [
        "none",
        "wavelet",
        "adain"
      ]
    },
    "tile_diffusion_stride": {
      "title": "Tile Diffusion Stride",
      "description": "Stride of sliding patch.",
      "default": 512,
      "type": "number",
      "minimum": 128,
      "maximum": 1024,
      "multipleOf": 1
    },
    "tile_vae_encoder_size": {
      "title": "Tile Vae Encoder Size",
      "description": "Size of latent image",
      "default": 1024,
      "type": "number",
      "minimum": 128,
      "maximum": 2048,
      "multipleOf": 1
    },
    "tile_vae": {
      "title": "Tile Vae",
      "description": "If specified, a patch-based sampling strategy will be used for VAE decoding.",
      "default": false,
      "type": "boolean"
    },
    "steps": {
      "title": "Steps",
      "description": "The number of steps to run the model for. The higher the number the better the quality and longer it will take to generate.",
      "default": 50,
      "type": "number",
      "minimum": 10,
      "maximum": 100,
      "multipleOf": 1
    },
    "t_min": {
      "title": "T Min",
      "description": "The starting point of uniform sampling strategy.",
      "default": 0.3333,
      "type": "number",
      "minimum": 0,
      "maximum": 1
    },
    "scale": {
      "title": "Scale",
      "description": "The scale of the output image. The higher the scale, the bigger the output image will be.",
      "default": 2,
      "type": "number",
      "minimum": 1,
      "maximum": 4,
      "multipleOf": 1
    },
    "tile_diffusion_size": {
      "title": "Tile Diffusion Size",
      "description": "Size of patch.",
      "default": 1024,
      "type": "number",
      "minimum": 256,
      "maximum": 2048,
      "multipleOf": 1
    },
    "seed": {
      "title": "Seed",
      "description": "Seed for reproducibility. Different seeds will make slightly different results.",
      "type": "integer"
    },
    "tile_vae_decoder_size": {
      "title": "Tile Vae Decoder Size",
      "description": "Size of VAE patch.",
      "default": 226,
      "type": "number",
      "minimum": 64,
      "maximum": 2048,
      "multipleOf": 1
    },
    "reference_image_url": {
      "type": "string",
      "format": "uri"
    }
  },
  "required": [
    "model_id",
    "reference_image_url"
  ],
  "additionalProperties": false
}

Browse schemas for every ArtEmotion model →

FAQ

How much does CCSR cost on ArtEmotion?

Credit-based pricing. You pay in ArtEmotion credits — every plan and top-up converts USD to credits at a fixed rate.

Do I get my credits back if CCSR fails?

Yes — failed generations are never charged. The credits are released back to your balance automatically.

Can I call CCSR from the API?

Yes. Use POST /api/v1/generate with model_id: "fal-ai/ccsr". See the API reference for the full schema.

Where are my generations stored?

Every output is saved to your personal Library. You can export or delete everything any time from Privacy & deletion.

Ready to generate with CCSR?

Start now →

No commitment. New accounts get 50 free credits on signup. See pricing.