Skip to content

Latest commit

 

History

History
56 lines (40 loc) · 14.8 KB

File metadata and controls

56 lines (40 loc) · 14.8 KB

FriendliCoreImage

(dedicated.image)

Overview

Available Operations

generate

Given a description, the model generates image(s).

Example Usage

import os

from friendli import SyncFriendli

with SyncFriendli(
    token=os.getenv("FRIENDLI_TOKEN", ""),
) as friendli:
    res = friendli.dedicated.image.generate(
        model="(endpoint-id)",
        num_inference_steps=10,
        prompt="An orange Lamborghini driving down a hill road at night with a beautiful ocean view in the background.",
        response_format="url",
    )

    # Handle response
    print(res)

Parameters

Parameter Type Required Description Example
model str ✔️ ID of target endpoint. If you want to send request to specific adapter, use the format "YOUR_ENDPOINT_ID:YOUR_ADAPTER_ROUTE". Otherwise, you can just use "YOUR_ENDPOINT_ID" alone. (endpoint-id)
num_inference_steps int ✔️ The number of inference steps to use during image generation. Supported range: [1, 50].
prompt str ✔️ A text description of the desired image(s).
x_friendli_team OptionalNullable[str] ID of team to run requests as (optional parameter).
guidance_scale OptionalNullable[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. This parameter may be irrelevant for certain models, such as FLUX.Schnell.
response_format OptionalNullable[models.DedicatedImageGenerationBodyResponseFormat] The format in which the generated image(s) will be returned. One of url(default), raw, png, jpeg, and jpg.
seed OptionalNullable[int] The seed to use for image generation.
retries Optional[utils.RetryConfig] Configuration to override the default retry behavior of the client.

Response

models.DedicatedImageGenerateSuccess

Errors

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