🚨New OSS nano-Banana competitor droped

🎉 Hunyuanimage-2.1 key features //hunyuan.tencent.com/ High quality generation: Efficiently produces ultra-high definition (2K) pictures with cinematic composition. Multilingual support: offers native support for Chinese and English requests. Advanced architecture: Building on a multimodal, single and two-stream-combined DIT backbone (diffusion transfer formator). Glyphic processing: Use the text reverting functions of BYT5 for improved accuracy of text generation. Flexible side conditions: Supports a variety of image pages (1: 1, 16: 9, 9:16, 4: 3, 3: 4, 3: 2, 2: 3). Rapid improvement: Write down the requests automatically to improve descriptive accuracy and visual quality. I can see that you have the complete and distilled models, each are approximately 34 GB, and an LLM contained on the repo