hvision-nku
/
storydiffusion
Consistent Self-Attention for Long-Range Image and Video Generation
Run hvision-nku/storydiffusion with an API
Input schema
Random seed. Leave blank to randomize the seed
Number of id images in total images. This should not exceed total number of line-separated prompts
- Default
- 3
Choose a model
- Default
- "Unstable"
Number of sample steps
- Default
- 25
- Minimum
- 20
- Maximum
- 50
Reference image for the character
Style template
- Default
- "Japanese Anime"
Select the comic style for the combined comic
- Default
- "Classic Comic Style"
Width of output image
- Default
- 768
Height of output image
- Default
- 768
The degree of Paired Attention at 32 x 32 self-attention layers
- Default
- 0.5
- Maximum
- 1
The degree of Paired Attention at 64 x 64 self-attention layers
- Default
- 0.5
- Maximum
- 1
Format of the output images
- Default
- "webp"
Scale for classifier-free guidance
- Default
- 5
- Minimum
- 0.1
- Maximum
- 10
Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality
- Default
- 80
- Maximum
- 100
Describe things you do not want to see in the output
- Default
- "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. 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.
- Default
- "at home, read new paper #at home, The newspaper says there is a treasure house in the forest.\non the road, near the forest\n[NC] The car on the road, near the forest #He drives to the forest in search of treasure.\n[NC]A tiger appeared in the forest, at night \nvery frightened, open mouth, in the forest, at night\nrunning very fast, in the forest, at night\n[NC] A house in the forest, at night #Suddenly, he discovers the treasure house!\nin the house filled with treasure, laughing, at night #He is overjoyed inside the house."
Style strength of Ref Image (%), only used if ref_image is provided
- Default
- 20
- Minimum
- 15
- Maximum
- 50
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'
- Default
- "a man, wearing black suit"