FLUX.1-Kontext [dev]

Try FLUX.1-Kontext [dev] in the Workbench

Run this model interactively, tune parameters, and compare outputs.

Model ID: flux-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
Context Length	0K (not applicable for vision model)
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.

Example request

Use the Workbench as a request builder: configure parameters for this model in the UI, then open the API tab to copy the exact cURL or Python call.

Sync
Async
Async with SSE

See the image editing reference for more details.

Minimal
All parameters

curl -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",
  "input_image": "https://hub.oxen.ai/api/repos/ox/Oxen-Character-Simple-Vector-Graphic/file/main/images/reference/bloxy_white_bg.png",
  "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"
}'

curl -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",
  "input_image": "https://hub.oxen.ai/api/repos/ox/Oxen-Character-Simple-Vector-Graphic/file/main/images/reference/bloxy_white_bg.png",
  "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",
  "aspect_ratio": "match_input_image",
  "num_inference_steps": 28,
  "guidance": 2.5,
  "output_format": "webp",
  "output_quality": 80,
  "disable_safety_checker": false
}'

See the async queue reference for more details.

Minimal
All parameters

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "flux-kontext-dev",
  "input_image": "https://hub.oxen.ai/api/repos/ox/Oxen-Character-Simple-Vector-Graphic/file/main/images/reference/bloxy_white_bg.png",
  "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"
}' | jq -r '.generations[0].generation_id')

# Poll the single generation until it 404s (terminal state).
while curl -s -o /dev/null -w "%{http_code}" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | grep -q "^200$"; do
  sleep 5
done
echo "Done. See the 'Async with SSE' tab to receive the result URL."

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "flux-kontext-dev",
  "input_image": "https://hub.oxen.ai/api/repos/ox/Oxen-Character-Simple-Vector-Graphic/file/main/images/reference/bloxy_white_bg.png",
  "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",
  "aspect_ratio": "match_input_image",
  "num_inference_steps": 28,
  "guidance": 2.5,
  "output_format": "webp",
  "output_quality": 80,
  "disable_safety_checker": false
}' | jq -r '.generations[0].generation_id')

# Poll the single generation until it 404s (terminal state).
while curl -s -o /dev/null -w "%{http_code}" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | grep -q "^200$"; do
  sleep 5
done
echo "Done. See the 'Async with SSE' tab to receive the result URL."

See the async queue reference for more details.

Minimal
All parameters

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "flux-kontext-dev",
  "input_image": "https://hub.oxen.ai/api/repos/ox/Oxen-Character-Simple-Vector-Graphic/file/main/images/reference/bloxy_white_bg.png",
  "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"
}' | jq -r '.generations[0].generation_id')

# Stream the SSE channel, grab the data line that follows a
# media_generation_completed event for our id, and pretty-print it.
curl -sN -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/events \
  | awk -v id="$GEN_ID" '
    /^event: media_generation_completed$/ { expect=1; next }
    /^data: / && expect {
      payload = substr($0, 7)
      if (index(payload, "\"generation_id\":\"" id "\"")) { print payload; exit }
      expect = 0
    }
  ' | jq .

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "flux-kontext-dev",
  "input_image": "https://hub.oxen.ai/api/repos/ox/Oxen-Character-Simple-Vector-Graphic/file/main/images/reference/bloxy_white_bg.png",
  "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",
  "aspect_ratio": "match_input_image",
  "num_inference_steps": 28,
  "guidance": 2.5,
  "output_format": "webp",
  "output_quality": 80,
  "disable_safety_checker": false
}' | jq -r '.generations[0].generation_id')

# Stream the SSE channel, grab the data line that follows a
# media_generation_completed event for our id, and pretty-print it.
curl -sN -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/events \
  | awk -v id="$GEN_ID" '
    /^event: media_generation_completed$/ { expect=1; next }
    /^data: / && expect {
      payload = substr($0, 7)
      if (index(payload, "\"generation_id\":\"" id "\"")) { print payload; exit }
      expect = 0
    }
  ' | jq .

Fetch model details

The models endpoint returns the full model object, including its json_request_schema.

curl -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/ai/models/flux-kontext-dev

Request parameters

Required parameters

Field	Type	Default	Description
`input_image`	`string`	`"https://hub.oxen.ai/api/repos/ox/Oxen-Character-Simple-Vector-Graphic/file/main/images/reference/bloxy_white_bg.png"`	Image to use as reference. Must be jpeg, png, gif, or webp. Format: uri.
`prompt`	`string`	`"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"`	Text description of what you want to generate, or the instruction on how to edit the given image.

Optional parameters

Field	Type	Default	Description
`aspect_ratio`	`string`	`"match_input_image"`	Aspect ratio of the generated image. Use ‘match_input_image’ to match the aspect ratio of the input image. One of: 1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21, match_input_image.
`num_inference_steps`	`integer`	`28`	Number of inference steps Range: 4 – 50.
`guidance`	`number`	`2.5`	Guidance scale for generation Range: 0 – 10.
`seed`	`integer`	—	Random seed for reproducible generation. Leave blank for random.
`output_format`	`string`	`"webp"`	Output image format One of: webp, jpg, png.
`output_quality`	`integer`	`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`	`false`	Disable NSFW safety checker

Inference API

Try FLUX.1-Kontext [dev] in the Workbench

​Example request

​Fetch model details

​Request parameters

​Required parameters

​Optional parameters

Example request

Fetch model details

Request parameters

Required parameters

Optional parameters