Submit a text-to-image task - sd_txt2img

更新时间:
复制 MD 格式

API description

Generates images from text using Stable Diffusion.

Prerequisites

If you have integrated the Video Factory SDK, see Previous Version SDK Reference.

Authorization

To obtain an AK/SK, see API Authorization.

Endpoint

https://openai.edu-aliyun.com

Path

/scc/sd_txt2img

Request headers

Name

Type

Description

X-SP-RESOURCE-CONFIG-ID

string

The ID of the resource pool configuration. This parameter is optional. For more information about the format, see Resource pool configuration parameters.

Request parameters

Name

Type

Description

stable_diffusion_model

string

The image generation model. This is the model file name on the platform.

sd_vae

string

The VAE decoder. Common options include the following:

Automatic

"None": Disables the VAE.

"sdxl_vae.safetensors": The VAE used with XL models.

clip_skip

int

The number of CLIP layers to skip at the end.

prompt

string

The positive prompt.

negtive_prompt

string

The negative prompt.

batch_size

integer

The number of images to generate in each batch.

steps

integer

Number of iterations

cfg_scale

double

Prompt relevance.

width

integer

The width of the image.

height

integer

The height of the image.

sampler_name

string

The sampler.

seed

long

The random seed.

alwayson_scripts

object

Input parameters for plugins.

controlnet

object

ControlNet parameters.

units

array

A list of control units.

module

string

The ControlNet preprocessor.

model

string

The ControlNet model.

input_image

string

The ControlNet reference image.

guidance_start

integer

The point at which ControlNet starts to take effect. The value ranges from 0 to 1. The default value is 0.

guidance_end

integer

The point at which ControlNet stops taking effect.

weight

double

The control strength. The value ranges from 0 to 2. A larger weight results in a more pronounced effect on the image. The default value is 1.

Data parameters

Name

Type

Description

taskId

string

The ID of the image generation task.

status

string

The task status. Valid values: `succeeded`: The task was successful. `failed`: The task failed. `running`: The task is in progress. `waiting`: The task is in a queue.