Recommended Prompts
score_9,score_8_up,score_7_up,source_anime
score_9,score_8_up,score_7_up,source_anime
Recommended Negative Prompts
worst quality,bad quality,jpeg artifacts,source_cartoon,3d,(censor),monochrome,blurry,lowres,watermark
worst quality,bad quality,jpeg artifacts,source_cartoon,3d,(censor),monochrome,blurry,lowres,watermark
Recommended Parameters
samplers | Euler a, DPM++ 2M Karras | |
steps | 30 | |
cfg | 7 | |
clip skip | 2 | |
resolution | 896×1192 |
Tips
- ADetailer face_yolov8n/s.pt can fix eyes
- The example images use a size of 896×1192.
Creator Sponsors
All sponsors are not affiliates of Diffus. Diffus provides an alternative online Stable Diffusion WebUI experience.
If you want to use more my checkpoint online generation, please visit here.
V9 Hyper12step
Please refer to the instructions on the right side of V9 Hyper12step for usage.
V9 released.
v8->v9
-
adjusted the facial data to make it more versatile, allowing for easier generation of faces across various ages.
-
added more NSFW materials.
-
attempted to reduce the generation of some unnecessary details.
hyper12step released.
about size
Various combinations from 768×768 to 1360×1360 can produce good images.