🤗A PyTorch-native and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.

Experimental demonstration for the Qwen/Qwen-Image-Edit-2511 model with lazy-loaded LoRA adapters supporting multi-image input editing. Users can upload one or more images (gallery format) and apply advanced edits such as pose transfer, anime conversion, or camera angle changes via natural language prompts. Features integrated Rerun SDK.

Demonstration for the Qwen-Image-Edit-2511 model with lazy-loaded LoRA adapters for advanced single- and multi-image editing. Supports 7 specialized LoRAs including photo-to-anime, multi-angle camera control, pose transfer (Any-Pose), upscaling, style transfer, light migration, and manga tone. Features fast inference (4 steps default).

Experimental demonstration for the Qwen/Qwen-Image-Edit-2511 model with lazy-loaded LoRA adapters for single-image editing tasks. Features specialized edits like photo-to-anime conversion and multi-angle transformations. Unique integration with Rerun SDK: outputs are visualized in an interactive viewer.

Demonstration for the Qwen/Qwen-Image-Edit-2511 model, specialized in object manipulation via lazy-loaded LoRA adapters. Supports adding or removing specific elements (e.g., logos, accessories, clothing) in single- or multi-image inputs while preserving lighting, realism, and background details. Features precise prompt control and fast inference.

Qwen Image Edit 2511 – The latest editing specialist. It achieves significant advances in character consistency and multi-person handling. It excels at preserving identity during imaginative edits, supports complex text rendering (Chinese & English), and integrates community LoRAs natively.