Build Smarter Agents with Nemotron 3 Nano Omni on FriendliAI — Explore models
API Reference
Model APIs
Dedicated
Container
Dataset & File
BetaFriendli SDK
curl --request POST \
--url http://localhost:8000/v1/images/edits \
--header 'Content-Type: application/json' \
--data '
{
"image": "@/path/to/file/image.png",
"prompt": "Add a red sports car in the foreground."
}
'{
"image": "<base64 encoded image>"
}Container image edits
Edit images with text prompts using Friendli Container. Upload an image and describe desired modifications to the self-hosted model on your GPUs.
curl --request POST \
--url http://localhost:8000/v1/images/edits \
--header 'Content-Type: application/json' \
--data '
{
"image": "@/path/to/file/image.png",
"prompt": "Add a red sports car in the foreground."
}
'{
"image": "<base64 encoded image>"
}Given an image and a description, the model edits the image.Documentation Index
Fetch the complete documentation index at: https://friendli.ai/docs/llms.txt
Use this file to discover all available pages before exploring further.
Body
The image(s) to edit. Must be in a supported image format.
- ImageInput · object
- ImageInput · object[]
Hide child attributes
Hide child attributes
An input image, provided either as a URL or a base64-encoded string. Maximum supported image size is 50 MiB.
"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"
"data:image/png;base64,..."
A text description of the desired image.
Routes the request to a specific adapter.
"(adapter-route)"
The number of inference steps to use during image generation. Defaults to 20. Supported range: [1, 50].
Adjusts the alignment of the generated image with the input prompt. Higher values (e.g., 8-10) make the output more faithful to the prompt, while lower values (e.g., 1-5) encourage more creative freedom. Defaults to 0. This parameter may be irrelevant for certain models, such as FLUX.Schnell.
The seed to use for image generation.
The format in which the generated image will be returned. One of raw and jpeg.
raw, jpeg Response
Successfully edited image.
The base64-encoded image.