Views
No views yet
tectonics.pytorch_lora_weights.safetensors: Diffusers format (use with diffusers library)pytorch_lora_weights_webui.safetensors: Kohya format (use with AUTOMATIC1111, ComfyUI, etc.)1from diffusers import FluxPipeline
2import torch
3
4# Load base model
5pipe = FluxPipeline.from_pretrained(
6 "black-forest-labs/FLUX.1-dev",
7 torch_dtype=torch.bfloat16
8)
9
10# Load LoRA weights (diffusers format)
11pipe.load_lora_weights("runchat/lora-528e51bb-51af-4f29-8c62-1b71bd92e946-o6p66f", weight_name="pytorch_lora_weights.safetensors")
12pipe = pipe.to("cuda")
13
14# Generate image
15prompt = "a photo of a tectonics style"
16image = pipe(prompt, num_inference_steps=50, guidance_scale=3.5).images[0]
17image.save("output.png")pytorch_lora_weights_webui.safetensors file and place it in your WebUI's LoRA directory.
Use the trigger word tectonics in your prompts.tectonics