Downloads · 30 days
13
18% of all-time downloads
magneticTileCrack
danildushenev/magneticTileCrack
magneticTileCrack is a text-to-image model from danildushenev. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as other.
All-time downloads
74
Public
Repo size
101 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors101 MB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Access
- Public
- Created
- Feb 7, 2026
- Updated
- Feb 7, 2026
- SHA
- d70c7e23
Base models
Model card
From the Hugging Face model README
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)
- Download
pytorch_lora_weights.safetensorsfrom this repo. - Put it into
ComfyUI/models/loras/. - 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.
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Fal Ai
- live
- Wavespeed
- live
- Created
- Feb 7, 2026
- Updated
- Feb 7, 2026