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
- 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.”
- Choose canvas width/height for your target platform.
- (Optional) Set a seed for repeatability.
- 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
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. | |
| size | string | No | 1024*1024 | 256 ~ 1536 per dimension | The size of the generated media in pixels (width*height). |
| seed | integer | No | -1 | -1 ~ 2147483647 | The random seed to use for the generation. -1 means a random seed will be used. |
| output_format | string | No | jpeg | jpeg, png, webp | The format of the output image. |
| enable_base64_output | boolean | No | false | - | 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_mode | boolean | No | false | - | 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
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |