Storydiffusion

Create a comic using a reference image and a description.

Try it in the Widget Center

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

Usage

Create a comic using a reference image (optional) and a description.

Input Parameters

NameTypeDescriptionDefaultRequired

sd_model

string

Choose a model

Unstable

ref_image

string

Reference image for the character. leave it empty for no reference generation

character_description

string

General description of the character. If ref_image above is provided, making sure trigger word 'img' is included in you character description. Use any word for class before 'img'. such as: 'man img' or 'woman img' or 'policeman img'. Example: 'a photo of a man/woman img'. The phrase 'img' is the trigger word.

a policeman img, wearing a white shirt

negative_prompt

string

Describe things you do not want to see in the output. The negative prompt should NOT contain the trigger word.

bad anatomy, bad hands, missing fingers, extra fingers, three hands, three legs, bad arms, missing legs, missing arms, poorly drawn face, bad face, fused face, cloned face, three crus, fused feet, fused thigh, extra crus, ugly fingers, horn, cartoon, cg, 3d, unreal, animate, amputation, disconnected limbs

comic_description

string

Comic Description. Each frame is divided by a new line. Only the first 10 prompts are valid for demo speed! For comic_description NOT using ref_image: (1) Support Typesetting Style and Captioning. By default, the prompt is used as the caption for each image. If you need to change the caption, add a '#' at the end of each line. Only the part after the '#' will be added as a caption to the image. (2) The [NC] symbol is used as a flag to indicate that no characters should be present in the generated scene images. If you want do that, prepend the '[NC]' at the beginning of the line. Note that [NC] is not supported when ref_image is provided.

at home, read new paper #at home, The newspaper says there is a treasure house in the forest. on the road, near the forest [NC] The car on the road, near the forest #He drives to the forest in search of treasure. [NC]A tiger appeared in the forest, at night very frightened, open mouth, in the forest, at night running very fast, in the forest, at night [NC] A house in the forest, at night #Suddenly, he discovers the treasure house! in the house filled with treasure, laughing, at night #He is overjoyed inside the house.

style_name

string

Style template

Japanese Anime

comic_style

string

Select the comic style for the combined comic

Classic Comic Style

style_strength_ratio

integer

Style strength of Ref Image (%), only used if ref_image is provided

20

image_width

integer

Width of output image

768

image_height

integer

Height of output image

768

num_steps

integer

Number of sample steps

25

guidance_scale

number

Scale for classifier-free guidance

5

seed

integer

Random seed. Leave blank to randomize the seed

sa32_setting

number

The degree of Paired Attention at 32 x 32 self-attention layers

0.5

sa64_setting

number

The degree of Paired Attention at 64 x 64 self-attention layers

0.5

num_ids

integer

Number of id images in total images. First `num_ids` picture descripton should not contains [NC] if ref_image is not None.This should not exceed total number of line-separated prompts

2

output_format

string

Format of the output images

jpg

output_quality

integer

Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality

80

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

{ // ref image:  https://image.myshell.ai/image/chat/embed_obj/255/202405090351/images.jpeg.jpeg
  "url": "https://image.myshell.ai/image/chat/embed_obj/255/202405090350/b779162b8ce34e53896a9ea492a6c279.jpeg"
}

Last updated