Stable Diffusion Transform

Transform images using the specified model ID from Civitai. With the given prompt and model, enable to transform the image based on the initial image.

Try it in the Widget Center

Click this url to try this widget and copy the Pro Config template.

Usage

Transform images using the specified model ID from Civitai. With the provided prompt and model, enable the transformation of images based on the initial image.

Input Parameters

NameTypeDescriptionDefaultRequired

image

string

The input image, can be a url or base64 sting

model

string

The model id from civitai (SD1.5, SDXL 1.0, PlaygroundV2). How to get it? Click on a model page on civitai, and copy the series number within the download link.

64094

prompt

string

The text prompt for image transformation. Add lora? add < lora:$id:$weight > to your prompt. `$id` is the series number and `$weight` is the lora weight you want (always set to 1.0). You can use multiple loras.

negative_prompt

string

The negative prompt for image transformation.

(worst quality, low quality:1.4),(malformed hands:1.4),(poorly drawn hands:1.4),(mutated fingers:1.4),(extra limbs:1.35),(poorly drawn face:1.4),bad leg,strange leg, poor eyes, full screen of face

sampler

string

Sampler for diffusion model inference

DPM++ 2M

resize_mode

string

Four modes for output shape calculation: (1) Keep: keep original shape, (2) Certain: based on input width/length (divisible by 32), (3,4) min/max ratio: keep aspect ratio, the resize factor is the min/max of (h/H, w/W).

certain

height

integer

Height of the transformed images

512

width

integer

Width of the transformed images

512

steps

integer

Steps for sampler to step whle sampling

25

cfg_scale

number

Classifier Free Guidance Scale - how strongly the image should conform to prompt - lower values produce more creative results. Default to 7.

7.0

seed

integer

Random seed for generation process. -1 means random seed

-1

clip_skip

integer

Early stopping parameter for CLIP model; 1 is stop at last layer as usual, 2 is stop at penultimate layer, etc.

1

denoising_strength

number

Strength of image transfomation during hires transform. High means more influence during transformation

0.7

Output Parameters

NameTypeDescriptionFile Type

url

string

The url of generated image, stored in the cloud. Only temporarily effective, will be cleared in a few hours.

image

Output Example

{
  "url": "https://image.myshell.ai/image/chat/embed_obj/40295/20240423/098f3f68bc2b4c42bb742add9efb2a2e.jpg"
}

Detailed Guidelines

  • Transform

    • Usage: Transform the initial image's size and style while preserving most of the original content.

      *(prompt: two dogs running in the rain.)

      The first image is the input init image, we transform the size and style in the following two images.*

    • Main parameter:

      • image : The input image, can be a url. Any size

      • model & prompt : Same as stable diffusion generation usage.

      • denoising_strength: Strength of image transfomation during hires transform. High means more influence during transformation

Last updated