import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2509", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("tarn59/extract_texture_qwen_image_edit_2509")
prompt = "Extract stone texture from the wall. Extract into a texture image."
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]Extract Texture
- Prompt
- Extract stone texture from the wall. Extract into a texture image.
- Prompt
- Extract birch wallpaper texture from tree trunks. Extract into a texture image.
- Prompt
- Extract wood panel texture from coffee mug. Extract into a texture image.
Model description
Extract a texture image from a given object. Works best if the texture is a repeated pattern.
Prompt: Extract {texture description} texture from the {object descrption}. Extract into a texture image. Example: Extract the fabric texture from the carpet. Extract into a texture image.
Also helps to call it a fabric or wallpaper texture.
Trigger words
You should use Extract {texture description} texture from the {object descrption}. Extract into a texture image. to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 1,774
Model tree for tarn59/extract_texture_qwen_image_edit_2509
Base model
Qwen/Qwen-Image-Edit-2509