FLUX.1 [dev]

https://mcp.app.layer.ai/mcp

execute_forge({
  "base_model_id": "flux",
  "prompt": "A crystal sword icon on a transparent background, game UI art",
  "batch_size": 4,
  "width": 1024,
  "height": 1024
})

# Start the generation — returns an inference id straight away.
curl -X POST https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/base-models/bfl-flux-1-dev/inferences \
  -H "Authorization: Bearer $LAYER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": "A crystal sword icon on a transparent background, game UI art"
      }'

# Poll until status is "complete" — the response then carries the asset URLs.
curl https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/inferences/$INFERENCE_ID \
  -H "Authorization: Bearer $LAYER_TOKEN"

prompt

string

Describe what to generate, or the change to make.

tileability

booleandefault false

Make the image repeat without a visible seam when tiled side by side.

negative_prompt

string

What to keep out of the result.

projection

string

Equirectangular is a 2:1 360 degree skybox whose sides meet and whose poles are settled.

projection_strength

numberdefault 10.5–1.5

How strongly the 360 projection is drawn. Lower keeps more of the model's own look.

aspect_ratio

enumdefault SQUARE_1K17 options

The shape and size of the output.

quality

enumdefault HIGHMEDIUM, HIGH

Higher levels render more detail, and can take longer and cost more.

seed

integer

The starting point for the model's randomness. The same seed and settings give the same result.

guidance_scale

numberdefault 3.51–20

How closely the result follows the prompt. Lower gives the model more freedom.

inference_steps

integerdefault 281–50

How many refinement passes the model makes. More add detail and take longer.

base_shift

numberdefault 0.50–2

Shifts sampling at small sizes. Higher favours overall composition over fine detail.

max_shift

numberdefault 1.150–2

Shifts sampling at large sizes. Higher favours overall composition over fine detail.

transparency

booleandefault false

Output the subject alone, with no backdrop behind it.

guidance_file_init_image

file[]

The image to modify

guidance_file_ip_adapter

file[]

Transfers the overall look of this image

guidance_file_pose

file[]

Copies the pose in this image

guidance_file_depth

file[]

Copies the depth layout of this image

guidance_file_canny

file[]

Follows the hard edges in this image

guidance_file_softedge_hed

file[]

Follows the soft edges in this image

guidance_file_lineart

file[]

Follows the lines in this drawing

output_fit

any

Trim the transparent margin, and place the image on a canvas of a fixed size.

prompt_language

string

The language the prompt is written in, so it reaches the model as you meant it.