Generate

Text-to-image, image-to-video, text-to-speech, and image-to-3D generation. Use Generate as the starting point for most workflows.

Every endpoint returns a job_id and has a matching GET …/status/{job_id} route, see Jobs. The fields output_format (webp, jpeg, or png), callback_url (a webhook), and server_id (Enterprise: pin to a dedicated pod) are accepted by every endpoint below.

Text → Image

POST /generate/image/v1, only prompt is required.

curl https://api.imagepipeline.io/generate/image/v1 \
  -H "X-API-Key: $IMAGEPIPELINE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "a person in a red jacket on a rooftop at golden hour",
    "width": 1024,
    "height": 1024,
    "output_format": "webp"
  }'

Field	Type	Default	Notes
prompt	string	,	Required. Text prompt describing the image.
width / height	integer	1024	Output dimensions in pixels (max 1024).
num_inference_steps	integer	model	Number of denoising steps. More = more detail, slower.
guidance_scale	number	model	How strictly to follow the prompt. Omit for the model default.
seed	integer	-1	-1 randomizes; set a value for reproducibility.
enhance_prompt	boolean	false	Run the prompt through a lightweight AI enhancer first.
logo_url	string	,	Public URL of a logo (PNG/WebP with transparency) to include.
palette	string[]	,	Brand colours as hex codes, e.g. ["#FF5733", "#3498DB"].
output_format	string	webp	webp, jpeg, or png.
profile_id	string	,	Apply an identity profile.
callback_url	string	,	Receive a webhook on completion.
server_id	string	,	Enterprise: pin to a dedicated pod.

Image → Video

POST /generate/video/v1, animate a still image (input_image required).

{
  "input_image": "https://.../still.webp",
  "prompt": "make this image come alive, cinematic motion",
  "duration_seconds": 2.0,
  "width": 896,
  "height": 512
}

Field	Type	Default	Notes
input_image	string	,	Required. Public URL of the image to animate.
prompt	string	cinematic motion	Describe the animation style or motion.
width / height	integer	896 / 512	Max 1536, must be divisible by 32.
duration_seconds	number	2.0	Video duration in seconds (0.1 to 10.0).
seed	integer	42	Seed for reproducibility.
callback_url	string	,	Webhook URL on completion.
server_id	string	,	Enterprise: pin to a dedicated pod.

Text → Speech

POST /generate/speech/v1, synthesize speech from text.

{ "text": "Welcome to ImagePipeline.", "language_id": "en", "exaggeration": 0.5 }

Field	Type	Default	Notes
text	string	,	Required. Text to convert to speech.
language_id	string	en	Language code, e.g. en, zh, ja, ko, he.
target_voice_path	string	,	Public URL of a reference voice audio file for cloning.
max_new_tokens	integer	256	Maximum tokens to generate.
exaggeration	number	0.5	Expressiveness (0.0 neutral to 1.0 maximum).
apply_watermark	boolean	true	Embed an inaudible audio watermark (recommended).
callback_url	string	,	Webhook URL on completion.
server_id	string	,	Enterprise: pin to a dedicated pod.

Image → 3D

POST /generate/3d/v1, turn an image into a 3D mesh (image_path required).

{ "image_path": "https://.../object.webp", "mode": "generate" }

Field	Type	Default	Notes
image_path	string	,	Required. Public URL of the input image.
mode	string	generate	generate (mesh only) or paint (texture and mesh).
mesh_save_name	string	,	Optional filename for the output mesh, e.g. model.obj.
painted_save_name	string	,	Optional filename for the textured mesh.
auto_unload	boolean	true	Unload the pipeline from GPU after completion.
callback_url	string	,	Webhook URL on completion.
server_id	string	,	Enterprise: pin to a dedicated pod.