Execute inference

curl --request POST \ --url https://api.app.layer.ai/api/v1/workspaces/{workspace_id}/inferences \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data ' { "model_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a", "prompt": "<string>", "width": 1, "height": 1, "batch_size": 4, "num_inference_steps": 1, "guidance_scale": 123, "prompt_strength": 0.5, "quality": "low", "sharpness": 123, "duration_seconds": 1, "generate_audio": true, "keep_audio": true, "fps": 1, "video_effects": [], "use_ta_pose": true, "include_textures": true, "quad_mesh": true, "pbr_materials": true, "low_poly": true, "generate_parts": true, "face_limit": 1, "stability": 0.5, "use_speaker_boost": true, "similarity_boost": 0.5, "style_exaggeration": 0.5, "speed": 1, "upscale_ratio": 123, "creativity": 123, "resemblance": 123, "vectorize": true, "remove_background": true, "reframe": true, "refill": true, "seed": -1, "guidance_files": [], "mask": { "file_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a", "for_transparency": true, "for_nontransparency": true, "edge_radius": 0 }, "session_name": "<string>" } '

{ "inference_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a", "status": "in_progress", "poll_interval_seconds": 123, "created_at": "2023-11-07T05:31:56Z", "estimated_price_creative_units": 123, "session_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a", "normalized_parameters": { "width": 123, "height": 123, "batch_size": 123, "num_inference_steps": 123, "guidance_scale": 123, "duration_seconds": 123, "fps": 123 } }

Authorizations

Authorization

string

header

required

Personal Access Token or OAuth2 JWT. Create a PAT at app.layer.ai → Settings → Personal Access Tokens.

Path Parameters

workspace_id

string<uuid>

required

Body

application/json

REST request body for executing an inference. workspace_id comes from path.

model_id

string<uuid>

required

Model/style ID to use for generation.

prompt

string | null

Text prompt.

Maximum string length: 100000

width

integer | null

Output width in pixels.

Required range: x > 0

height

integer | null

Output height in pixels.

Required range: x > 0

batch_size

integer

default:4

Number of outputs (1-16).

Required range: 1 <= x <= 16

num_inference_steps

integer | null

Number of diffusion steps.

Required range: x > 0

guidance_scale

number | null

Guidance scale (CFG).

prompt_strength

number | null

Prompt strength for img2img (0-1).

Required range: 0 <= x <= 1

quality

enum<string> | null

Quality level: low, medium, or high.

Available options:

low,

medium,

high

sharpness

number | null

Output sharpness.

duration_seconds

number | null

Video duration in seconds.

Required range: x > 0

generate_audio

boolean | null

Generate audio with video.

keep_audio

boolean | null

Keep audio from input video.

fps

integer | null

FPS for LTX video generation (e.g. 25 or 50).

Required range: x > 0

video_effects

ForgeVideoEffectInput · object[]

Video effects to apply.

Show child attributes

use_ta_pose

boolean | null

Use T/A pose for 3D.

include_textures

boolean | null

Include textures in 3D output.

quad_mesh

boolean | null

Generate quad mesh.

pbr_materials

boolean | null

Generate PBR materials.

low_poly

boolean | null

Generate low-poly mesh.

generate_parts

boolean | null

Generate separate parts.

face_limit

integer | null

Face/polygon limit for 3D mesh.

Required range: x > 0

stability

number | null

Audio stability (0-1).

Required range: 0 <= x <= 1

use_speaker_boost

boolean | null

Boost speaker clarity.

similarity_boost

number | null

Voice similarity boost (0-1).

Required range: 0 <= x <= 1

style_exaggeration

number | null

Style exaggeration (0-1).

Required range: 0 <= x <= 1

speed

number | null

Speech speed multiplier.

Required range: x > 0

upscale_ratio

number | null

Upscale factor (e.g. 2.0, 4.0).

creativity

number | null

Creative variation strength for upscaling.

resemblance

number | null

Resemblance to original for upscaling.

vectorize

boolean | null

Vectorize the output image.

remove_background

boolean | null

Remove background from output.

reframe

boolean | null

Reframe/extend the image.

refill

boolean | null

Outpaint/refill transparent areas.

seed

integer

default:-1

Random seed. -1 for random.

guidance_files

ForgeGuidanceFileInput · object[]

Reference images/files to guide generation.

Maximum array length: 20

Show child attributes

mask

ForgeMaskInput · object

Mask for inpainting/outpainting.

Show child attributes

session_name

string | null

Session name.

Maximum string length: 255

Response

Successful Response

inference_id

string<uuid>

required

Unique identifier for this forge run.

status

enum<string>

required

Current status: IN_PROGRESS.

Available options:

in_progress,

complete,

failed,

cancelled,

deleted

poll_interval_seconds

integer

required

Suggested polling interval in seconds.

created_at

string<date-time>

required

Timestamp of when the run was created.

estimated_price_creative_units

number | null

Estimated price in Creative Units.

session_id

string<uuid> | null

Session ID the run was added to, if a session was specified.

normalized_parameters

NormalizedInferenceParameters · object

Actual parameters used after model-specific normalization and defaults.

Show child attributes

Overview

Workspaces

Models

Workflows

Inferences

Files

Execute inference

Authorizations

Path Parameters

Body

Response