导语：UiT 架构探路者，底牌还没亮。 雷峰网(公众号：雷峰网)讯 2026 年 5 月，智象未来开源了文生图模型 HiDream-O1-Image（8B），直接登顶 Artificial Analysis 开源模型全球第一，Elo 1187 ...

Since I'm not at all used to models that use natural language, this is an attempt to get used to it little by little using anima, which can also use danbooru tags. Personally, I find SDWebUI-based ...

After buying a GPU, I decided to start with image generation, as expected. I'll introduce the journey and the local services and tools that I ended up using. * The large amount of memory is for ...

It's not just Google's Gemini 3, Nano Banana Pro and Anthropic's Claude Opus 4.5 we have to be thankful around the Thanksgiving holiday (at least here in the U.S.) No, German AI startup Black Forest ...

Models supported: SDXL, Flux, LTX-Video, HunyuanVideo (t2v), Cosmos, Lumina Image 2.0, Wan2.1 (t2v and i2v), Chroma, HiDream, Stable Diffusion 3, Cosmos-Predict2 ...

DeepSeek has introduced its recent model DeepSeek-R1, showing divergence from OpenAI’s ChatGPT, suggesting an open-source alternative to users. This paper analyzes the architecture of DeepSeek-R1, ...