Venice Image Editing

Four endpoints, all operating on existing images:

For text-to-image generation, see venice-image-generate.

Shared rules

• Input image accepts base64 string, file upload (multipart for /image/multi-edit), or HTTPS URL (for edit + multi-edit + background-remove).
• File size < 25 MB. Image dimensions must be between 65,536 (256×256 equivalent) and 33,177,600 pixels (~5,761×5,761). Upscale caps at 16,777,216 pixels after scaling.
• HTTPS URLs must be publicly reachable from Venice's network.
• All four endpoints return the image as binary, never JSON. There is no return_binary field on edit / multi-edit / upscale / background-remove (that flag only exists on /image/generate). /image/edit and /image/multi-edit return image/png, image/jpeg, or image/webp depending on output_format; /image/upscale and /image/background-remove always return image/png.

/image/edit

Edit one image with a short, descriptive prompt.

curl https://api.venice.ai/api/v1/image/edit \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "firered-image-edit",
    "prompt": "Change the color of the sky to a sunrise",
    "image": "iVBORw0KGgoAAAANSUhEUg...",
    "aspect_ratio": "16:9",
    "safe_mode": true
  }'

Good prompts: "remove the tree", "add sunglasses to the cat", "make the sky a vivid orange sunrise".

Edit-capable model IDs change often. Read them from GET /models?type=inpaint
rather than pinning a literal, and note that older IDs like qwen-edit have
been retired in favor of qwen-image-2-edit and friends.

/image/multi-edit

Combine several images into one with a prompt. The first image is the base; the rest are layers / masks / references. The minimum is 1 image and the maximum is model-specific — read capabilities.maxInputImages from GET /models.

Field name: /image/multi-edit takes modelId, not model. This is the only image endpoint that uses modelId as the primary field name.

JSON (base64 or URLs)

{
  "modelId": "firered-image-edit",
  "prompt": "Place the person from image 2 onto the beach in image 1",
  "images": [
    "https://example.com/beach.jpg",
    "data:image/png;base64,iVBOR..."
  ],
  "safe_mode": true
}

Multipart (file upload)

POST /image/multi-edit
Content-Type: multipart/form-data

--boundary
Content-Disposition: form-data; name="modelId"

firered-image-edit
--boundary
Content-Disposition: form-data; name="prompt"

Place the person from image 2 onto the beach in image 1
--boundary
Content-Disposition: form-data; name="images"; filename="base.jpg"
Content-Type: image/jpeg

<bytes>
--boundary
Content-Disposition: form-data; name="images"; filename="subject.png"
Content-Type: image/png

<bytes>
--boundary--

/image/upscale

Upscale 2× or 4×. This endpoint has three fields.

Breaking change: /image/upscale no longer accepts enhance,
enhanceCreativity, enhancePrompt, or replication, and no longer accepts
scale: 1. The enhancer knobs were replaced by a single creativity field
with a much narrower range. If you are sending the old fields, drop them.

curl https://api.venice.ai/api/v1/image/upscale \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image": "iVBORw0KGgo...",
    "scale": 4,
    "creativity": 0.01
  }'

Also available as multipart/form-data. Response is the upscaled image as
binary image/png.

/image/background-remove

Produce a transparent PNG cutout.

# With base64
curl https://api.venice.ai/api/v1/image/background-remove \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"image": "iVBOR..."}'

# With a URL
curl https://api.venice.ai/api/v1/image/background-remove \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"image_url": "https://example.com/photo.jpg"}'

Send either image (base64 / file) or image_url. Response is image/png with alpha channel.

Error behavior (all four endpoints)

(413 and 422 are not documented for these image paths in the OpenAPI spec — a 413 from the platform may still appear if you exceed ingress limits, but treat 400 / 415 as the primary failure surface.)

Gotchas

• /image/multi-edit images[] explicitly accepts data:image/...;base64,... URLs or plain base64. For /image/edit and /image/upscale, send base64 as a plain string unless the docs say otherwise — if your client adds a data: prefix and you get a 400, strip it.
• For multipart /image/multi-edit, the field name is images and you send multiple parts with the same field name — order matters (base first).
• Field-name asymmetry: /image/edit prefers model (modelId is a deprecated alias). /image/multi-edit accepts only modelId. Get the name right per endpoint — sending the wrong one is a 400.
• /image/upscale with scale=4 on a large input is silently clamped to stay under 16 MP.
• creativity on /image/upscale is not the old enhanceCreativity under a new name. Its usable range is 0 to 0.02, so port enhanceCreativity: 0.5 as creativity: 0.02 (the maximum), not as 0.5.
• enhance_prompt on edit / multi-edit bills extra credits whenever a rewrite is produced. Leave it off for latency-sensitive or cost-sensitive calls.
• safe_mode: true can blur otherwise valid inputs if the source image trips content classifiers; switch to false (and handle the legal/ToS consequences yourself) when you control the input.
• /image/background-remove takes either image or image_url, not both.