About FLUX.1-Kontext [dev]
black-forest-labs/FLUX.1-Kontext-dev is a 12 billion parameter multimodal LVM (vision model) designed for high-fidelity image editing and generation using both text and image inputs.
It excels in iterative image editing, maintaining character, style, and object consistency over multiple successive edits with minimal visual drift. The model reliably performs both local and global modifications, and is noted for its robust contextual understanding and ability to process instructions for precise regional edits or full scene transformations.
Some other noteworthy features of black-forest-labs/FLUX.1-Kontext-dev include:
- Preserving unique elements (like characters or objects) across different scenes and environments, even after several edits.
- Generating novel images with style or character references guided by either text or example images.
| Metric | Value |
|---|---|
| Parameter Count | 12 billion |
| Mixture of Experts | No |
| Multilingual | No |
| Quantized* | Yes |
| Precision* | FP8 |
*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.
Ready to build with FLUX.1-Kontext [dev]?
Try FLUX.1-Kontext [dev] in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/images/edit \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "flux-kontext-dev",
"prompt": "High quality illustration of the character riding a cow, with a text bubble saying '\''Woohoo!'\'' - preserve all colors and traits of the original character, and render the cow in the same style",
"input_image": "https://hub.oxen.ai/api/repos/ox/Oxen-Character-Simple-Vector-Graphic/file/main/images/reference/bloxy_white_bg.png",
"aspect_ratio": "16:9",
"num_inference_steps": 28,
"guidance": 2.5,
"output_format": "webp",
"output_quality": 80,
"disable_safety_checker": false
}'Request parameters
Every field FLUX.1-Kontext [dev] accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/images/edit| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Text description of what you want to generate, or the instruction on how to edit the given image. |
input_image | stringuri | Yes | — | Image to use as reference. Must be jpeg, png, gif, or webp. |
aspect_ratio | string | No | "16:9" | 1:116:921:93:22:34:55:43:44:39:169:21match_input_image |
num_inference_steps | integer | No | 28 | Number of inference steps Range: 4 – 50 |
guidance | number | No | 2.5 | Guidance scale for generation Range: 0 – 10 |
seed | integer | No | — | Random seed for reproducible generation. Leave blank for random. |
output_format | string | No | "webp" | Output image formatwebpjpgpng |
output_quality | integer | No | 80 | Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs Range: 0 – 100 |
disable_safety_checker | boolean | No | false | Disable NSFW safety checker |