Editing

Instruction-based image editing via natural-language prompts. Change scenes, swap objects, and adjust composition without masks.

POST /edit/image/v1, edit input_image according to prompt.

curl https://api.imagepipeline.io/edit/image/v1 \
  -H "X-API-Key: $IMAGEPIPELINE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input_image": "https://.../photo.webp",
    "prompt": "change the jacket to navy blue and add soft rim lighting",
    "faster_inference": true
  }'

input_image accepts a single URL string, or an array of URLs (for example a model image plus a product image to composite).

Field	Type	Default	Notes
prompt	string	,	Required. The natural-language edit instruction.
input_image	string | string[]	,	Image(s) to edit. A single URL, or an array of URLs.
mode	string	,	Processing mode. Use anime to convert a photo to an illustration.
faster_inference	boolean	true	Use the Lightning LoRA distillation for speed.
refine_strength	number	,	Z-Image Turbo refinement pass after editing (0.0 to 1.0).
num_inference_steps	integer	model	Diffusion steps (1 to 100). Higher = better, slower.
guidance_scale	number	model	Classifier-free guidance (0.0 to 20.0). 0 disables it.
cfg_norm_strength	number	,	CFG normalization strength (0.0 to 1.0).
tone_correction	number	,	Post-edit tonal correction strength (0.0 to 1.0).
product_saturation	number	,	Saturation multiplier applied to the product image (image 2).
has_text	boolean	,	Whether the image contains visible text, logos, or labels.
has_product	boolean	,	Whether the image contains a physical product as the subject.
seed	integer	-1	-1 randomizes; set a value for reproducibility.
palette	string[]	,	Brand colours as hex codes, e.g. ["#FF5733"].
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.

Returns a job_id; poll GET /edit/image/v1/status/{job_id} or use a webhook.