🔥BREAKING! DiffSynth-Studio just dropped: Qwen-Image-i2L — the first open-source suite that turns a single image into a custom LoRA! 🖼️➡️🧠 Choose your flavor: 🎨 Style – pure aesthetic extraction (2.4B) 🧩 Coarse – captures content + style (7.9B) ✨ Fine – 1024x1024 detail

Z-Image is a multi-functional workflow collection that supports high-definition zoom, text-to-image conversion, partial image redrawing, full image redrawing, and the Canny+Depth+Pose controller. It's incredibly powerful. For video tutorials, please see: youtu.be/ZgGnE0hjsQo

Try the new editing model demo.🥳

Z-Image outputs 4K resolution images directly. Download the "New" workflow here: huggingface.co/dx8152/Qwen-Ed… YouTube: youtu.be/sCeBkphogsM

Qwen-Image-Edit 2511 Gaussian Splash 3D Camera Motion Tongyi Lab ModelScope Youtube： youtu.be/9Vyxjty9Qao Download Link: huggingface.co/dx8152/Qwen-Ed…

Flux2 Klein performs exceptionally well, surpassing the performance of the trained LoRA in many aspects, whether for image editing or text-to-image conversion. I highly recommend testing it out. Tutorial link: youtu.be/F7gokUkzSnc

Qwen3-TTS is officially live. We’ve open-sourced the full family—VoiceDesign, CustomVoice, and Base—bringing high quality to the open community. - 5 models (0.6B & 1.8B) - Free-form voice design & cloning - Support for 10 languages - SOTA 12Hz tokenizer for high compression -

Qwen3-TTS has been officially released as open source, voice design, and voice cloning. I've created a custom WebUI interface for your convenience Tongyi Lab ModelScope Tutorial: youtu.be/1dV2VTJXwo8 ⬇️github.com/hero8152/Qwen3…

The Qwen-Image Global Challenge is about to officially open. Get your datasets ready. We are looking for the best stylization LoRAs in the world. High-performance rewards for high-performance creativity. Stay sharp. Details drop in a few days.

Ready to make this February legendary? 🚀✨The Qwen-Image LoRA Training Competition is officially LIVE! We’ve teamed up with Tongyi Lab and Qwen to bring you some absolutely grand prizes:📱 iPhone 17 Pro Max (512GB) 🎮 Sony PS5 Pro 🛍️ $800 Shopping Cards (or

Building an AI workstation from scratch, generating images using the free APIs of local ComfyUI and ModelScope Tongyi Lab ModelScope Tutorial link: youtu.be/MgQMGHyMLRg Experience and download the project online: modelscope.cn/studios/Daniel… huggingface.co/spaces/dx8152/…

Klein's LoRA: Everything Becomes Real, Comics Become Real, Images Add Detail Run online: runninghub.ai/post/202039302…

Qwen Image 2.0 boasts incredible text processing capabilities, a two-in-one model combining image generation and editing, enabling text modification, image fusion, lighting adjustments, and material replacement. Tongyi Lab ModelScope Try it now: chat.qwen.ai

Major open-source release! Flux2-Klein detail enhancement for LoRA, suitable for various images. Tutorial here: youtu.be/ZXN6haTJb3I, more examples here: youtu.be/I5HDM2oZpJ0. Download here: huggingface.co/dx8152/Flux2-K… ModelScope