🎨 Qwen-Image-2.1 Demo

Text-to-image demo for Qwen/Qwen-Image-2.1 — a 7B DiT model for unified text-to-image generation, editing and RGBA (transparent) output.

Looking for the quantized weights for local generation? Grab GGUF / Safetensors / MLX quantizations from abenzerps/Qwen-Image-2.1-Uncensored-Quantized and run them in ComfyUI with the ComfyUI-GGUF loader — see the README in that repo for the recommended Q4_K_M setup.

Quantized weights (GGUF / MLX / FP8): abenzerps/Qwen-Image-2.1-Uncensored-Quantized