General description of the character. If ref_image above is provided, making sure to follow the class word you want to customize with the trigger word 'img', such as: 'man img' or 'woman img' or 'girl img'
Negative prompt
Describe things you do not want to see in the output
Comic description
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.
Style Name
Style template
Comic Style
Select the comic style for the combined comic
Style strength ratio
15
20
50
Style strength of Ref Image (%), only used if ref_image is provided
Image Width
Width of output image
Image Height
Height of output image
Num steps
20
25
50
Number of sample steps
Guidance scale
0.1
5
10
Scale for classifier-free guidance
Seed
Random seed. Leave blank to randomize the seed
Sa32 setting
0
0.5
1
The degree of Paired Attention at 32 x 32 self-attention layers
Sa64 setting
0
0.5
1
The degree of Paired Attention at 64 x 64 self-attention layers
Num ids
Number of id images in total images. This should not exceed total number of line-separated prompts
Output Format
Format of the output images
Output quality
0
80
100
Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality
Sd Model
Choose a model
Ref image
Reference image for the character
Character description
General description of the character. If ref_image above is provided, making sure to follow the class word you want to customize with the trigger word 'img', such as: 'man img' or 'woman img' or 'girl img'
Negative prompt
Describe things you do not want to see in the output
Comic description
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.
Style Name
Style template
Comic Style
Select the comic style for the combined comic
Style strength ratio
15
20
50
Style strength of Ref Image (%), only used if ref_image is provided
Image Width
Width of output image
Image Height
Height of output image
Num steps
20
25
50
Number of sample steps
Guidance scale
0.1
5
10
Scale for classifier-free guidance
Seed
Random seed. Leave blank to randomize the seed
Sa32 setting
0
0.5
1
The degree of Paired Attention at 32 x 32 self-attention layers
Sa64 setting
0
0.5
1
The degree of Paired Attention at 64 x 64 self-attention layers
Num ids
Number of id images in total images. This should not exceed total number of line-separated prompts
Output Format
Format of the output images
Output quality
0
80
100
Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality
