V2 update!: Fal.ai helped out providing compute to train a better checkpoint! We've just finished training and are happy to release the v2/544p model. This checkpoint should produce significantly ...

Prompt outputs failed validation DualCLIPLoader: Value not in list: clip_name1: 'clip_1.safetensors' not in [] Value not in list: clip_name2: 'llava_1lama3_fp8_scaled.safetensors' not in [] Value not ...

In conclusion, Hunyuan-DiT is a major breakthrough in text-to-image generation, especially for Chinese prompts. It provides outstanding performance in producing detailed and contextually accurate ...

Chinese video gaming and social media giant Tencent launched an upgraded version of its large language model with text-to-image generation that is open source for enterprises and individuals.

Chinese video gaming and social media giant Tencent Holdings has launched a text-to-video generation tool based on its Hunyuan artificial intelligence (AI) foundation model, joining an ...