Finetuned from 50 high quality chosen images.
This model has a monster bias producing great monster with great fidelity.
You don't need any specific trigger words. Any monster related prompt will result in a strong level of monstrosity.
Based on SD1.5
Please use vae-ft-mse-840000-ema-recommended VAE for optimal results
Use 768x768 for best results
Prompt Examples:
Prompt: scary monster, dark fantasy art in the style of greg rutkowski and craig mullins. hyper detailed 8 k ultra realistic painting movie still unreal engine 5 render with nanite as a path tracing reflections raytracing cinematic lighting wide angle exterior photography by zdzisław beksinski trending on pinterest furaffinity octane colored brushstrokes concept studio portrait black background
Negative prompt: 3D, cartoon
Steps: 36, Sampler: Euler a, CFG scale: 7, Seed: 1058838011, Size: 768x768,
Description
Initial Release
FAQ
Comments (2)
nice model
This model does not seem to work in SD1.4. 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: 2.87s
Torch active/reserved: 4277/5168 MiB, Sys VRAM: 7464/8192 MiB (91.11%)
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.