Skip to content

README.md

Latest commit

 

History

History
119 lines (90 loc) · 43.6 KB

README.md

File metadata and controls

119 lines (90 loc) · 43.6 KB

Container.Image

Overview

Available Operations

generate

Given a description, the model generates image.

Example Usage

import os

from friendli import SyncFriendli

with SyncFriendli(
    token=os.getenv("FRIENDLI_TOKEN", ""),
) as friendli:
    res = friendli.container.image.generate(
        prompt="An orange Lamborghini driving down a hill road at night with a beautiful ocean view in the background.",
        model="(adapter-route)",
        num_inference_steps=10,
        guidance_scale=3.5,
        control_images=[
            {
                "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png",
            },
        ],
    )

    # Handle response
    print(res)

Parameters

Parameter Type Required Description Example
prompt str ✔️ A text description of the desired image.
model OptionalNullable[str] ➖ Routes the request to a specific adapter. (adapter-route)
num_inference_steps Optional[int] ➖ The number of inference steps to use during image generation. Defaults to 20. Supported range: [1, 50].
guidance_scale Optional[float] ➖ 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.
seed OptionalNullable[int] ➖ The seed to use for image generation.
response_format OptionalNullable[models.ContainerImageGenerationBodyResponseFormat] ➖ The format in which the generated image will be returned. One of raw and jpeg.
control_images List[models.ImageInput] ➖ Optional input images used to condition or guide the generation process (e.g., for ControlNet or image editing models). This field is only applicable when using ControlNet or image editing models.
controlnet_weights List[float] ➖ A list of weights that determine the influence of each ControlNet model in the generation process. Each value must be within [0, 1], where 0 disables the corresponding ControlNet and 1 applies it fully. When multiple ControlNet models are used, the list length must match the number of control images. If omitted, all ControlNet models default to full influence (1.0). This field is only applicable when using ControlNet models.
retries Optional[utils.RetryConfig] ➖ Configuration to override the default retry behavior of the client.
server_url Optional[str] ➖ An optional server URL to use. http://localhost:8080

Response

models.ContainerImageGenerateSuccess

Errors

Error Type Status Code Content Type
models.SDKError 4XX, 5XX */*

edit

Given an image and a description, the model edits the image.

Example Usage

import os

from friendli import SyncFriendli

with SyncFriendli(
    token=os.getenv("FRIENDLI_TOKEN", ""),
) as friendli:
    res = friendli.container.image.edit(
        image=[
            {
                "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png",
            },
        ],
        prompt="Add a red sports car in the foreground.",
        model="(adapter-route)",
        num_inference_steps=20,
        guidance_scale=0,
    )

    # Handle response
    print(res)

Parameters

Parameter Type Required Description Example
image models.ContainerImageEditBodyImage ✔️ The image(s) to edit. Must be in a supported image format.
prompt str ✔️ A text description of the desired image.
model OptionalNullable[str] ➖ Routes the request to a specific adapter. (adapter-route)
num_inference_steps Optional[int] ➖ The number of inference steps to use during image generation. Defaults to 20. Supported range: [1, 50].
guidance_scale Optional[float] ➖ 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.
seed OptionalNullable[int] ➖ The seed to use for image generation.
response_format OptionalNullable[models.ContainerImageEditBodyResponseFormat] ➖ The format in which the generated image will be returned. One of raw and jpeg.
retries Optional[utils.RetryConfig] ➖ Configuration to override the default retry behavior of the client.
server_url Optional[str] ➖ An optional server URL to use. http://localhost:8080

Response

models.ContainerImageGenerateSuccess

Errors

Error Type Status Code Content Type
models.SDKError 4XX, 5XX */*