Verified: 3 months ago
SafeTensor
Type | |
Stats | 71 29 3 |
Reviews | (7) |
Published | Feb 16, 2025 |
Base Model | |
Training | Steps: 8,450 Epochs: 10 |
Usage Tips | Clip Skip: 2 Strength: 0.8 |
Trigger Words | spiderman_bodysuit, gloves mask spider web print, white spider logo |
Hash | AutoV2 3117E40637 |
About the trigger words, here's the instruction:
To trigger the outfit: spiderman_bodysuit, gloves
To trigger the mask: mask
For the web pattern and the spider logo: spider web print, white spider logo
Negative prompt: watermark, username, instagram username
Precautions:
If the generated image is blurry, try to decrease model weight.
For some reasons, when using this model with 2.5D checkpoint models (Aniverse, Rev Animated, ...), the result image is blurry and contains lots of artifacts. (I appreciate any comment about this problem. It would help me a lot in the future)By reducing CFG scale to 5, it fixed the blurry problemMake sure to set CLIP skip to 2. Otherwise, it may generate blobs of poor quality images.