This model can create vector style art. Please see the sample images.
Model used: revAnimated
Steps: 30
Sampler: DPM++ 2M Karras
CFG scale: 6–7 max.
Clip skip: 1 or 2
Prompt: tshee00d, vector style, solo, looking at viewer, simple background, sitting, no humans, headphones, animal, mouth hold, bear, black background, cable, animal focus <lora:tshee00d-000008:1>
Negative prompt: bad_quality, easynegative
Steps: 30, Sampler: Euler a, CFG scale: 7, Seed: 3113972125, Size: 512x768, Model hash: 4199bcdd14, Model: best_revAnimated_v122, Clip skip: 2, Version: v1.2.1
Download badquality.pt, EasyNegative.safetensors and put them into the embeddings' folder.
Use tshee00d, vector style as triggers.
Description
V1
FAQ
Comments (4)
Amazing..
Thank you :D
Hi , can help me someone, i have this error:
NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.
Time taken: 0.29s
Torch active/reserved: 2239/2482 MiB, Sys VRAM: 4629/12288 MiB (37.67%)
thanks for any help
Try to update Automatic1111 to the latest version. It may solve this problem.
Awesome!
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.