danildushenev/magneticTileCrack

FLUX.2-dev LoRA adapter.

Files

• pytorch_lora_weights.safetensors (SHA256: 1b1c77fcf469deaa22cbbf64321c613ce387b0ca10ba466587c429a99166cef8)

Usage (Diffusers)

import torch
from diffusers import Flux2Pipeline

pipe = Flux2Pipeline.from_pretrained("black-forest-labs/FLUX.2-dev", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("danildushenev/magneticTileCrack", weight_name="pytorch_lora_weights.safetensors")
image = pipe("your prompt", num_inference_steps=24, guidance_scale=2.5).images[0]
image.save("result.png")

Usage (ComfyUI)

1. Download pytorch_lora_weights.safetensors from this repo.
2. Put it into ComfyUI/models/loras/.
3. In workflow use LoRA Loader and set this file.

Trigger text: a photo of Magnetic Tile crack

Generated on 2026-02-07 20:41:51Z.