Hello, creators and innovators,
This week, as we share the latest from our lab, the real magic happened beyond it - in the hands of developers, artists, and builders around the world.
From stunning image edits with Qwen-Image, to expressive, style-shifting generations with Wan, the open-source community is turning our foundational models into something extraordinary.
These aren't just LoRAs. They're personal expressions of what's possible when open models meet bold imagination.
👉 Subscribe to The Tongyi Weekly and never miss a release:
Subscribe Now →
📣 Model Release & Updates
Introducing Qwen DeepResearch 2511, a major upgrade to our DeepResearch model
Qwen DeepResearch 2511 is now live and ready to transform how you explore, analyze, and synthesize knowledge.
- Dual Mode: Choose Normal for speed, or flip to Advanced and let the AI dive deep - spending extra time for a more thorough analysis.
- File Uploads Enabled: Now you can easily upload your documents or images for the AI to analyze!
- Boosted Search Power: Drastically improved search efficiency & depth. It reads more, understands deeper, and delivers better answers - in less time.
- Precise Report Control: Command the report format - word count, paragraphs, & content! Get comprehensive reports with enhanced citation reliability.
All-New UX: Our new decoupled architecture delivers a smoother, more responsive user experience.
👉 Try it now:
✨ Community Spotlights
Light Restoration (built on Qwen-Image-Edit-2509): Qwen-Image-Edit-2509-Light_restorationfrom dx8152
This LoRA from dx8152 removes unwanted shadows and fixes exposure with astonishing naturalness - perfect for photographers and digital artists.
👉 Try it Here
🎥 Video demo
Photo Upscale (built on Qwen-Image-Edit-2509): Qwen-Edit-2509-Upscale-LoRA from vafipas663
Need to rescue those blurry, low-res, or noisy old photos? This Upscale-LoRA from vafipas663 does an amazing job at enhancing photography, fixing noise, and destroying JPEG artifacts.
👉 Try it Here
Skin Realism (built on Qwen-Image-Edit-2509): qwen-edit-skin from tlennon-ie
Want your portraits to have a natural skin texture? This LoRA from tlennon-ie specifically addresses the nuances of human skin, adding detail and realism that may not be present in the original generations.
👉 Try it Here
Photo-to-Anime (built on Qwen-Image-Edit-2509): Qwen-Image-Edit-2509-Photo-to-Animefrom autoweeb
This LoRA from autoweeb turns any photo into a stunning anime image. Just try a simple prompt like "transform into anime" and watch the magic happen.
👉 Try it Here
Generate the Next Scene (built on Qwen-Image-Edit-2509): next-scene-qwen-image-lora-2509 from lovis93
lovis93's "Next Scene" LoRA understands camera motion - dolly shots, push-ins, pans - and generates seamless transitions between frames. V2 is even better.
👉 Try it Here
3D Chibi (built on Qwen-Image-Edit-2509): Qwen-Edit-3DChibi-LoRA from rsshekhawat
Ready to turn your entire photo library into an adorable 3D Chibi world? rsshekhawat's LoRA creates high-quality, highly detailed 3D Chibi Style images.
👉 Try it Here
Background White to Scene (built on Qwen-Image-Edit-2509): Qwen-Image-Edit-2509-White_to_Scene from dx8152
Tired of product shots stuck on white? This LoRA from dx8152 is an Image Fusion tool that lets you take any object and seamlessly place it into a brand new scene using trigger words like "change white background to scene".
👉 Try it Here
In-Scene Image Editing (built on Qwen-Image-Edit): qwen-image-edit-inscene-lora from flymy-ai
Want to change the action in your photo without breaking the scene? flymy-ai's InScene LoRA is specialized to understand complex in-scene commands, maintain coherence, and handle object positioning like a pro.
👉 Try it Here
Apply Texture (built on Qwen-Image-Edit-2509): apply_texture_qwen_image_edit_2509 from tarn59
tarn59's wild "Apply Texture" LoRA lets you apply any texture to any object. Just use Apply ... texture to ... to trigger the image generation!
👉 Try it Here
Animal to Human Avatar (built on Qwen-Image-Edit-2509): Qwen-Edit-2509-Anishift-LoRA from hiru13do37
Ever wondered what your pet would look like as a cool human? hiru13do37's Anishift LoRA transforms animals into hyper-stylized human avatars - with personality.
👉 Try it Here
De-Cartoon Everything (built on Qwen-Image-Edit-2509): QwenEdit-Anything2Real_Alpha from lrzjason
This LoRA from lrzjason is designed to convert illustrations, anime, cartoons, paintings, and other non-photorealistic images into convincing photographs while preserving the original composition and content.
👉 Try it Here
https://huggingface.co/lrzjason/QwenEdit-Anything2Real_Alpha
Fast Image Editing (built on Qwen-Image-Edit): eigen-banana-qwen-image-edit from eigen-ai-labs
eigen-ai-labs dropped Eigen-Banana - optimized for fast, high-quality image editing with text prompts. This model enables efficient text-guided image transformations with reduced inference steps while maintaining excellent quality. (Non-commercial use only.)
👉 Try it Here
Push-In Camera (built on Wan2.1): Motion-Lora-Camera-Push-In-Wan-14B-720p-I2V from lovis93
This LoRA from lovis93 was trained on 100 clips to introduce realistic, high-quality push-in drone camera motion into your generations, enhancing your creations by delivering natural camera dynamics across various styles and scenes.
👉 Try it Here
Slow-Motion Enhancement (built on Wan2.2): ComfyUI-PainterI2V from 绘画小子(Douyin creator)
ComfyUI-PainterI2V from 绘画小子(Douyin creator) specifically fixes the slow-motion issue in 4-step LoRAs (e.g., lightx2v) with reduced slow-motion drag, enhanced camera movement, optimized single-frame image-to-video workflows, and plug & play features.
👉 Try it Here
📬 Want More? Stay Updated.
Every week, we bring you:
- New model releases & upgrades
- AI research breakthroughs
- Open-source tools you can use today
- Community highlights that inspire
👉 Subscribe to The Tongyi Weekly and never miss a release.
Thank you for being part of this journey.
Tongyi Lab is a research institution under Alibaba Group dedicated to artificial intelligence and foundation models, focusing on the research, development, and innovative applications of AI models across diverse domains. Its research spans large language models (LLMs), multimodal understanding and generation, visual AIGC, speech technologies, and more.
Top comments (0)