Flux Kontext Dev
Edit images using Flux Kontext with prompt-based instructions. Supports acceleration modes, configurable inference steps, guidance scale, multiple output formats, and flexible resolution modes.
Quick Start
Requires an each::labs API key. Get one at eachlabs.ai.
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "flux-kontext-dev",
"version": "0.0.1",
"input": {
"image_url": "https://example.com/photo.jpg",
"prompt": "Change the person's shirt color to bright red",
"num_images": 1,
"output_format": "jpeg"
}
}'
Parameters
| Parameter |
Type |
Default |
Description |
| acceleration |
string |
none |
Generation speed. enum: none, regular, high |
| enable_safety_checker |
boolean |
true |
If set to true, the safety checker will be enabled |
| enhance_prompt |
boolean |
false |
Whether to enhance the prompt for better results |
| guidance_scale |
number |
2.5 |
CFG scale for prompt adherence |
| image_url |
string |
|
The URL of the image to edit |
| num_images |
integer |
1 |
The number of images to generate |
| num_inference_steps |
integer |
28 |
The number of inference steps to perform |
| output_format |
string |
jpeg |
Output format. enum: jpeg, png |
| prompt |
string |
|
The prompt to edit the image |
| resolution_mode |
string |
match_input |
How output resolution is set. enum: auto, match_input, 1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21 |
| seed |
string |
|
Seed for reproducible results |
Examples
Object replacement with acceleration:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "flux-kontext-dev",
"version": "0.0.1",
"input": {
"image_url": "https://example.com/desk-setup.jpg",
"prompt": "Replace the laptop with a vintage typewriter",
"acceleration": "regular",
"num_images": 1,
"guidance_scale": 3.0,
"output_format": "png"
}
}'
Style transformation with multiple outputs:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "flux-kontext-dev",
"version": "0.0.1",
"input": {
"image_url": "https://example.com/cityscape.jpg",
"prompt": "Transform into a Studio Ghibli anime art style with soft pastel colors",
"num_images": 3,
"acceleration": "high",
"enhance_prompt": true,
"resolution_mode": "16:9",
"seed": "12345"
}
}'
Related Models
Documentation
1---2name: flux-kontext-dev3description: Flux Kontext Dev. Edit images using Flux Kontext with prompt-based instructions and configurable LoRA-like controls. Triggers: flux, kontext, image edit, flux edit, image editing4---56# Flux Kontext Dev78Edit images using Flux Kontext with prompt-based instructions. Supports acceleration modes, configurable inference steps, guidance scale, multiple output formats, and flexible resolution modes.910## Quick Start1112> Requires an each::labs API key. Get one at [eachlabs.ai](https://eachlabs.ai).1314```bash15curl -X POST https://api.eachlabs.ai/v1/prediction \16 -H "Content-Type: application/json" \17 -H "X-API-Key: $EACHLABS_API_KEY" \18 -d '{19 "model": "flux-kontext-dev",20 "version": "0.0.1",21 "input": {22 "image_url": "https://example.com/photo.jpg",23 "prompt": "Change the person's shirt color to bright red",24 "num_images": 1,25 "output_format": "jpeg"26 }27 }'28```2930## Parameters3132| Parameter | Type | Default | Description |33|-----------|------|---------|-------------|34| acceleration | string | none | Generation speed. enum: none, regular, high |35| enable_safety_checker | boolean | true | If set to true, the safety checker will be enabled |36| enhance_prompt | boolean | false | Whether to enhance the prompt for better results |37| guidance_scale | number | 2.5 | CFG scale for prompt adherence |38| image_url | string | | The URL of the image to edit |39| num_images | integer | 1 | The number of images to generate |40| num_inference_steps | integer | 28 | The number of inference steps to perform |41| output_format | string | jpeg | Output format. enum: jpeg, png |42| prompt | string | | The prompt to edit the image |43| resolution_mode | string | match_input | How output resolution is set. enum: auto, match_input, 1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21 |44| seed | string | | Seed for reproducible results |4546## Examples4748**Object replacement with acceleration:**49```bash50curl -X POST https://api.eachlabs.ai/v1/prediction \51 -H "Content-Type: application/json" \52 -H "X-API-Key: $EACHLABS_API_KEY" \53 -d '{54 "model": "flux-kontext-dev",55 "version": "0.0.1",56 "input": {57 "image_url": "https://example.com/desk-setup.jpg",58 "prompt": "Replace the laptop with a vintage typewriter",59 "acceleration": "regular",60 "num_images": 1,61 "guidance_scale": 3.0,62 "output_format": "png"63 }64 }'65```6667**Style transformation with multiple outputs:**68```bash69curl -X POST https://api.eachlabs.ai/v1/prediction \70 -H "Content-Type: application/json" \71 -H "X-API-Key: $EACHLABS_API_KEY" \72 -d '{73 "model": "flux-kontext-dev",74 "version": "0.0.1",75 "input": {76 "image_url": "https://example.com/cityscape.jpg",77 "prompt": "Transform into a Studio Ghibli anime art style with soft pastel colors",78 "num_images": 3,79 "acceleration": "high",80 "enhance_prompt": true,81 "resolution_mode": "16:9",82 "seed": "12345"83 }84 }'85```8687## Related Models8889- [qwen-image-edit-plus](../qwen-image-edit-plus/) - Qwen-based image editing90- [qwen-ai-image-edit](../qwen-ai-image-edit/) - Standard Qwen image editing91- [reve-edit](../reve-edit/) - Reve image editing9293## Documentation9495- [each::labs Docs](https://docs.eachlabs.ai)96- [API Reference](https://docs.eachlabs.ai/api/overview)
awesome-genmedia