Chroma

Chroma

Playground

Try it on WavespeedAI!

Chroma enables fully uncensored image generation for creative expression and artistic freedom. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Chroma — Text-to-Image

Chroma is a fully uncensored image generation versatile image generator for portraits, products, and scene renders. It’s tuned for crisp detail, pleasing color separation, and stable composition—great for ads, thumbnails, story art, and concept frames.

Highlights

  • Clean, high-contrast renders with natural lighting and color harmony
  • Strong prompt adherence for people, props, and environments
  • Wide canvas support via freeform width/height (post-crop friendly)
  • Fast, predictable outputs for batch or single-shot creation

Inputs & Parameters

  • prompt (required): Describe subject, style, lighting, camera, and mood.
  • size: Set width and height freely (e.g., 1024x1322), up to 1536×1536.
  • seed:
    • -1 = random seed (varied results)
    • Any non-negative integer = reproducible output
  • output_format: jpeg , png, or webp.

How to Use

  1. Write a tight prompt with subject + style + lighting + composition. Example: “A character-driven portrait of a middle-aged craftsman in a rustic workshop, shallow depth of field, golden hour rim light, 50mm photo, editorial realism.”
  2. Choose canvas width/height for your target platform.
  3. (Optional) Set a seed for repeatability.
  4. Pick output_format and Run. Iterate by tweaking prompt or seed.

Prompting Tips

  • Structure: [subject] + [context] + [style] + [lighting] + [camera] + [mood].
  • For portraits, add: “soft key light, catchlights, subtle skin texture, shallow DOF.”
  • For products, add: “studio sweep background, three-point lighting, reflective control.”
  • Keep negatives concise (e.g., “blurry, extra fingers, watermark, text”).
  • Lock a seed once you like the look; only change details you intend to vary.

Output Guidance

  • Prefer power-of-two-ish sides (1024, 1280, 1536) for speed/quality balance.
  • Use png for transparency or sharp graphics; jpeg/webp for compact files.
  • Upscale later if you need 2K/4K (try Ultimate Image Upscaler).

Pricing

  • $0.015 per image

Notes

  • Commercial use is allowed per WaveSpeedAI terms.
  • Some prompts may be adjusted for safety/quality. If output diverges, simplify wording and iterate with seeds.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/chroma" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "size": "1024*1024",
    "seed": -1,
    "output_format": "jpeg",
    "enable_base64_output": false,
    "enable_sync_mode": false
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-The positive prompt for the generation.
sizestringNo1024*1024256 ~ 1536 per dimensionThe size of the generated media in pixels (width*height).
seedintegerNo-1-1 ~ 2147483647The random seed to use for the generation. -1 means a random seed will be used.
output_formatstringNojpegjpeg, png, webpThe format of the output image.
enable_base64_outputbooleanNofalse-If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.
enable_sync_modebooleanNofalse-If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

© 2025 WaveSpeedAI. All rights reserved.