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("wonwizard/flux_lora_cute_korean_girl")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]FLUX.1-dev LoRA cute korean girl
This repository provides a checkpoint with trained LoRA cute korean girl for FLUX.1-dev model by Black Forest Labs
prompt : cute girl
Comfyui workflow (Drop this image on comfyui)
Currently flux lora may have issues as it is all in early state and first version. Lora file is placed in ComfyUI/models/loras and workflow file can be dragged and dropped into comfyui. If you're seeing errors, update your comfyui.
If you use fp8, download fp8.safetensors
License
lora.safetensors falls under the FLUX.1 [dev] Non-Commercial License
- Downloads last month
- 81
Model tree for wonwizard/flux_lora_cute_korean_girl
Base model
black-forest-labs/FLUX.1-dev