How to use furaidosu/dott-4k-v4-qwen-image-2512_10 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image-2512", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("furaidosu/dott-4k-v4-qwen-image-2512_10") prompt = "A small-town street in Los Quirquinchos, Santa Fe, Argentina, shown with wide rippling dirt roads stretching in curved diagonals. Low single-story houses line both sides, their simple facades bending outward with elongated windows and shallow doorframes. Large leafy trees rise in exaggerated arcs along the sidewalks, casting stretched shadows across the uneven ground. Wooden and concrete utility poles lean at impossible angles, with cables twisting overhead in looping curves. Two clear routes appear: the main street running forward in a sweeping distorted line, and a secondary side street branching off to the left between bowed fences and low garden walls. Shallow drainage ditches follow the edges of the road, their contours bending softly. A parked old pickup truck sits at a tilted angle near a corner, its metal surface subtly warped. Street signs and small front yards distort toward an upward-curving horizon, giving the quiet rural town a spacious yet impossibly curved appearance." image = pipe(prompt).images[0]
The community tab is the place to discuss and collaborate with the HF community!
