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("cocktailpeanut/kaiji-dev2pro")
prompt = "kaiji style"
image = pipe(prompt).images[0]kaiji-dev2pro
A Flux LoRA trained on a local computer with Fluxgym
- Prompt
- kaiji style
Trigger words
You should use kaiji style to trigger the image generation.
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
- 6
Model tree for cocktailpeanut/kaiji-dev2pro
Base model
black-forest-labs/FLUX.1-dev