OpenDataArena/MMFineReason-1.8M-Qwen3-VL-235B-Thinking Viewer • Updated 17 days ago • 1.81M • 4.29k • 119
Shaping capabilities with token-level data filtering Paper • 2601.21571 • Published 18 days ago • 26
Running on CPU Upgrade 949 Omni Image Editor đź–Ľ 949 Image edit, text to image, image upscale, remove watermark
Running on Zero Featured 1.43k Qwen Image Multiple Angles 3D Camera 🎥 1.43k Adjust the viewpoint of any image with 3D camera controls
view article Article Architectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeek 20 days ago • 43
view article Article Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective 21 days ago • 55
Running on Zero MCP Featured 503 FLUX.2 [Klein] 9B đź’» 503 Generate or edit images from text prompts with optional source images
Runtime error Featured 1.41k Qwen3-TTS Demo 🎙 1.41k Generate speech from text with voice design, cloning, or speakers