API docs / Image models
qwen-image-edit API
Edit images using text prompts with specialized capabilities for precise text editing in both Chinese and English while preserving font, size, and style. Supports both semantic editing (IP creation, object rotation, style transfer, novel view synthesis) and appearance editing (adding, removing, or modifying specific elements while keeping other regions unchanged). Enables comprehensive image modifications including background changes, clothing adjustments, object insertion/removal, and bilingual text manipulation within images.
- Model id
qwen/qwen-image-edit- Provider
- qwen
- Output
- Image
- Price
- From 11 credits per run, the same as on voor.ai. Options such as length or resolution can change it.
Request
POST https://voor.ai/v1/generations with "model": "qwen/qwen-image-edit". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.
curl https://voor.ai/v1/generations \
-H "Authorization: Bearer $VOOR_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "qwen/qwen-image-edit",
"input": {
"prompt": "A red fox standing in fresh snow at golden hour, soft light",
"reference_images": [
"https://example.com/input.png"
]
},
"callback_url": "https://example.com/webhooks/voor"
}'
# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
-H "Authorization: Bearer $VOOR_API_KEY"Input parameters
| Name | Type | Details |
|---|---|---|
promptrequired | string | Text instruction on how to edit the given image. |
reference_imagesrequired | array of URLs | Image to use as reference. Must be jpeg, png, gif, or webp. Up to 1 files · Accepts image/* |
seed | number | Random seed. Set for reproducible generation |
output_format | string | Default: One of: webp, jpg, png |
go_fast | boolean | Run faster predictions with additional optimizations. Default: |
output_quality | number | Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs Default: Min 0 · Max 100 |