API docs / Image models
flux-redux-dev API
Creates variations of existing images while preserving key elements of the original. Takes an input image as conditioning instead of text prompts, generating new versions that maintain the essence of the original while allowing for creative exploration and design iteration.
- Model id
black-forest-labs/flux-redux-dev- Provider
- Flux AI
- Output
- Image
- Price
- From 9 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": "black-forest-labs/flux-redux-dev". 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": "black-forest-labs/flux-redux-dev",
"input": {
"redux_image": [
"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 |
|---|---|---|
aspect_ratio | string | Default: One of: 1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21 |
output_count | number | Number of outputs to generate Default: Min 1 · Max 4 |
seed | number | Random seed. Set for reproducible generation |
guidance | number | Guidance for generated image Default: Min 0 · Max 10 |
steps | number | Number of denoising steps. Recommended range is 28-50 Default: Min 1 · Max 50 |
output_format | string | Default: One of: webp, jpg, png |
megapixels | string | Default: One of: 1, 0.25 |
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 |
redux_imagerequired | array of URLs | Input image to condition your output on. This replaces prompt for FLUX.1 Redux models Up to 1 files · Accepts image/* |