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("kythours/kitou")
prompt = "hwxjos man walks down a quiet alley, shadows stretching behind him."
image = pipe(prompt).images[0]kitou
A Flux LoRA trained on a local computer with Fluxgym
- Prompt
- hwxjos man walks down a quiet alley, shadows stretching behind him.
- Prompt
- hwxjos man ties his boots as the morning light fills the room.
- Prompt
- hwxjos man smokes alone on a balcony overlooking the city.
- Prompt
- hwxjos man lifts a backpack and steps onto the train.
Trigger words
You should use owxjos 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
- 34
Model tree for kythours/kitou
Base model
black-forest-labs/FLUX.1-dev