--- license: apache-2.0 base_model: - Qwen/Qwen-Image-Edit-2511 base_model_relation: quantized library_name: diffusers tags: - sdnq - qwen_image - 4-bit --- 4 bit (UINT4 with SVD rank 32) quantization of [Qwen/Qwen-Image-Edit-2511](https://huggingface.co/Qwen/Qwen-Image-Edit-2511) using [SDNQ](https://github.com/Disty0/sdnq). Usage: ``` pip install sdnq ``` ```py import torch import diffusers from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers from sdnq.common import use_torch_compile as triton_is_available from sdnq.loader import apply_sdnq_options_to_model pipe = diffusers.QwenImageEditPlusPipeline.from_pretrained("Disty0/Qwen-Image-Edit-2511-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16) # Enable INT8 MatMul for AMD, Intel ARC and Nvidia GPUs: if triton_is_available and (torch.cuda.is_available() or torch.xpu.is_available()): pipe.transformer = apply_sdnq_options_to_model(pipe.transformer, use_quantized_matmul=True) pipe.text_encoder = apply_sdnq_options_to_model(pipe.text_encoder, use_quantized_matmul=True) # pipe.transformer = torch.compile(pipe.transformer) # optional for faster speeds pipe.enable_model_cpu_offload() pipe.set_progress_bar_config(disable=None) image1 = Image.open("input1.png") image2 = Image.open("input2.png") prompt = "The magician bear is on the left, the alchemist bear is on the right, facing each other in the central park square." inputs = { "image": [image1, image2], "prompt": prompt, "generator": torch.manual_seed(0), "true_cfg_scale": 4.0, "negative_prompt": " ", "num_inference_steps": 40, "guidance_scale": 1.0, "num_images_per_prompt": 1, } with torch.inference_mode(): output = pipeline(**inputs) output_image = output.images[0] output_image.save("qwen-image-edit-2511-sdnq-uint4-svd-r32.png") ```
