From 52b87fca23acedc399d062d593bec388aee9926a Mon Sep 17 00:00:00 2001 From: Phospheneser <2388840666@qq.com> Date: Tue, 20 Oct 2026 16:42:42 +0000 Subject: [PATCH] docs: announce MOSI API Platform availability --- README.md | 4 ++++ README_ZH.md | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/README.md b/README.md index e31e8a3..010a6d1 100644 --- a/README.md +++ b/README.md @@ -14,6 +14,8 @@   Hugging Face Spaces · Demo   + MOSI API Platform +   Homepage   Technical Report @@ -36,6 +38,8 @@ ## News +- **[2026-10-20]** 🚀 The **MOSS-Image** series is now available on the [MOSI API Platform](https://platform.mosi.cn/?utm_source=github&utm_medium=readme&utm_campaign=imageapi). Try it in the Playground or integrate it through the API. + - **[2026-10-19]** 📄 The [MOSS-Image Technical Report](https://arxiv.org/abs/2610.23374) is now available on arXiv. If you find our work useful, please support us with an [upvote on Hugging Face Papers](https://huggingface.co/papers/2610.23374)! 🤗 - **[2026-10-18]** 🛠️ [KohakuMossTrainer](https://github.com/KohakuBlueleaf/KohakuMossTrainer) has been released, offering full fine-tuning and LyCORIS training (including LoRA) for **MOSS-Image-Base** and **MOSS-Image-SFT**. It features extensive optimizer support, mixed-precision training (BF16/FP16/FP8/MXFP8/INT8), multi-GPU training (DDP/FSDP/pipeline parallelism), optimized kernels, and CPU offloading, enabling adapter training with as little as **6GB VRAM**. It supports Windows, Linux, NVIDIA GPUs (SM70–SM120), and Intel Arc GPUs. See the [GitHub repository](https://github.com/KohakuBlueleaf/KohakuMossTrainer) for details. diff --git a/README_ZH.md b/README_ZH.md index fa08da3..4883937 100644 --- a/README_ZH.md +++ b/README_ZH.md @@ -14,6 +14,8 @@   Hugging Face Spaces · Demo   + MOSI API Platform +   Homepage   Technical Report @@ -37,6 +39,8 @@ ## 动态 +- **[2026-10-20]** 🚀 **MOSS-Image** 系列现已上线 [MOSI API Platform](https://platform.mosi.cn/?utm_source=github&utm_medium=readme&utm_campaign=imageapi)，支持在 Playground 在线体验或通过 API 接入。 + - **[2026-10-19]** 📄 [MOSS-Image 技术报告](https://arxiv.org/abs/2610.23374)已在 arXiv 公开。如果我们的工作对你有帮助，欢迎在 [Hugging Face Papers 上为我们点赞（upvote）](https://huggingface.co/papers/2610.23374)，感谢支持！🤗 - **[2026-10-18]** 🛠️ [KohakuMossTrainer](https://github.com/KohakuBlueleaf/KohakuMossTrainer) 已发布，支持 **MOSS-Image-Base** 和 **MOSS-Image-SFT** 的全参数微调与 LyCORIS 训练（包括 LoRA）。它提供丰富的优化器、混合精度训练（BF16/FP16/FP8/MXFP8/INT8）、多 GPU 训练（DDP/FSDP/流水线并行）、优化算子及 CPU 卸载，适配器训练最低可使用 **6GB 显存**。支持 Windows、Linux、NVIDIA GPU（SM70–SM120）和 Intel Arc GPU。详见 [GitHub 仓库](https://github.com/KohakuBlueleaf/KohakuMossTrainer)。