Nvidia Chrono Edit
Playground
Try it on WavespeedAI!NVIDIA Chrono Edit is a state-of-the-art image-to-image AI editor that turns photos into stylized edits and retouches with a few clicks. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
NVIDIA ChronoEdit — Physics-aware Image Editing
ChronoEdit performs edits by reasoning through a short “imagined motion” between the original and the requested change. That temporal reasoning helps keep geometry, lighting, shadows, and contacts consistent in the final image.
Highlights
- Consistency-first edits: pose, lighting, reflections, and shadows stay believable.
- Works with one input image plus a natural-language instruction.
- Reproducible results with seed control; quick iteration for creative teams.
- Production-friendly outputs in JPEG, PNG, or WEBP; optional BASE64 and sync return.
Parameters
-
prompt: Describe the change you want, not general style fluff. Example: replace the plastic mug with a clear glass half-filled with tea; keep same angle and morning light.
-
image: Source image URL or upload. Use a clean, well-lit photo for best fidelity.
-
seed: Integer for determinism. Same prompt + image + seed gives the same result. Use −1 to randomize.
-
output_format: jpeg for compact distribution, png for lossless editing, webp for web delivery.
How to Use
- Upload the source image.
- Write a concrete prompt that states the target edit and what must be preserved.
- Set seed if you need reproducibility.
- Choose output_format.
- Run and review. If something drifts, tighten the prompt and fix the seed.
Prompting Tips
- Be explicit about conservation: keep camera angle, keep morning sunlight, keep the person’s pose.
- State the edit as a physical change: swap, add, remove, change material, change color.
- If lighting must change, say it clearly; otherwise the model will preserve the original light.
- For faces or text areas, crop tighter to the region before editing for crisper results.
Pricing
Per run: $0.02
Quality Notes
- Input quality sets the ceiling. Soft, noisy, or heavily compressed sources limit realism.
- For large pose or object changes, iterate with fixed seed and small prompt adjustments.
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/nvidia/chrono-edit" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"seed": -1,
"output_format": "jpeg",
"enable_base64_output": false,
"enable_sync_mode": false
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${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. | |
| image | string | Yes | - | The image to generate an image from. | |
| 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 | 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 |