- 谁
- vLLM
- 引文
🎉 Day-0 support for @MiniMax_AI’s MiniMax-H3-Image in vLLM-Omni!
发生了什么
vLLM-Omni 增加了对 MiniMax-H3-Image 的首日支持，可在 NVIDIA 和 AMD GPU 上运行。文章介绍，这款开放权重模型支持图像生成与编辑、约 16 兆像素的原生图像，以及在发布配方中每次请求最多使用 9 张图像进行多参考图编辑。文章还提到，提示词可达 4,096 个 token，并支持密集文本渲染。
接下来读什么
查看这件事的完整进展vLLM-Omni Adds GPU Support for MiniMax H3-Image🎉 Day-0 support for @MiniMax_AI’s MiniMax-H3-Image in vLLM-Omni!
Available on both NVIDIA and AMD GPUs from Day 0.
One open-weight model for generation + editing:
- Native ~16MP images
- Multi-reference editing: up to 9 images per request in the release recipe
- 4,096-token prompts and dense text rendering
在 X 查看被引用的帖子4K image generation in 10 seconds! ⚡
Meet MiniMax H3-Image.
16 million pixel resolution. Stunning realism. Precise prompt following & editing. Up to 16 reference images. All in 10 seconds.
And it's open-weight. 🚀
Available now via our API, MiniMax Code, and Hailuo AI — with 50% off 16MP+ generations during launch week!
Can't wait to see what you create. 🔥
Hugging Face: huggingface.co/MiniMaxAI/Mini…
API: platform.minimax.io/docs/guid…
MiniMax Code: code.minimax.io/about
这件事到目前为止
vLLM-Omni supports MiniMax-H3-Image on NVIDIA and AMD GPUs from day one, and vLLM says it is adding NVIDIA Vera Rubin support with native 4K generation in 0.87 seconds. The original release recipe supports multi-reference editing with up to nine images per request. vLLM also described the open-weight model as supporting image generation and editing, native images of about 16 megapixels, 4,096-token prompts, and dense text rendering. Its latest post congratulated MiniMax on H3-Image taking the top spot among open-weight image editing models in Artificial Analysis.