import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("CosmicCrafter/horror-tattoos-by-cosmic")
prompt = "a tattoo of a skull with flames on a mans back"
image = pipe(prompt).images[0]Horror Tattoos by cosmic
A Flux LoRA trained on a local computer with Fluxgym
- Prompt
- a tattoo of a skull with flames on a mans back
- Prompt
- a woman fully covered in scary tattoos
Trigger words
No trigger words defined.
Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, Forge, etc.
Weights for this model are available in Safetensors format.
- Downloads last month
- 22
Model tree for CosmicCrafter/horror-tattoos-by-cosmic
Base model
black-forest-labs/FLUX.1-dev