update readme

Author: helloyongyang

README.md

@@ -39,13 +39,13 @@ Besides the contributions from the LightX2V team, we have received contributions
 
 ## :fire: Latest News
 
-- **December 31, 2025:** 🚀 We support the [Qwen-Image-2512](https://huggingface.co/Qwen/Qwen-Image-2512) text-to-image model since Day 0. Our [HuggingFace](https://huggingface.co/lightx2v/Qwen-Image-2512-Lightning) has been updated with CFG / step-distilled LoRA.
+- **December 31, 2025:** 🚀 We support the [Qwen-Image-2512](https://huggingface.co/Qwen/Qwen-Image-2512) text-to-image model since Day 0. Our [HuggingFace](https://huggingface.co/lightx2v/Qwen-Image-2512-Lightning) has been updated with CFG / step-distilled LoRA. Usage examples can be found [here](https://github.com/ModelTC/LightX2V/tree/main/examples/qwen_image).
 
 - **December 27, 2025:** 🚀 Supported deployment on MThreads MUSA.
 
 - **December 25, 2025:** 🚀 Supported deployment on AMD ROCm and Ascend 910B.
 
-- **December 23, 2025:** 🚀 We support the [Qwen-Image-Edit-2511](https://huggingface.co/Qwen/Qwen-Image-Edit-2511) image editing model since Day 0. On a single H100 GPU, LightX2V delivers approximately 1.4× speedup. We support for CFG parallelism, Ulysses parallelism, and efficient offloading technologies. Our [HuggingFace](https://huggingface.co/lightx2v/Qwen-Image-Edit-2511-Lightning) has been updated with CFG / step-distilled LoRA and FP8 weights. Usage examples can be found in the [Python scripts](https://github.com/ModelTC/LightX2V/tree/main/examples/qwen_image). Combined with LightX2V, 4-step CFG / step distillation, and the FP8 model, the maximum acceleration can reach up to approximately 42×. Feel free to try [LightX2V Online Service](https://x2v.light-ai.top/login) with *Image to Image* and *Qwen-Image-Edit-2511* model.
+- **December 23, 2025:** 🚀 We support the [Qwen-Image-Edit-2511](https://huggingface.co/Qwen/Qwen-Image-Edit-2511) image editing model since Day 0. On a single H100 GPU, LightX2V delivers approximately 1.4× speedup. We support for CFG parallelism, Ulysses parallelism, and efficient offloading technologies. Our [HuggingFace](https://huggingface.co/lightx2v/Qwen-Image-Edit-2511-Lightning) has been updated with CFG / step-distilled LoRA and FP8 weights. Usage examples can be found [here](https://github.com/ModelTC/LightX2V/tree/main/examples/qwen_image). Combined with LightX2V, 4-step CFG / step distillation, and the FP8 model, the maximum acceleration can reach up to approximately 42×. Feel free to try [LightX2V Online Service](https://x2v.light-ai.top/login) with *Image to Image* and *Qwen-Image-Edit-2511* model.
 
 - **December 22, 2025:** 🚀 Added **Wan2.1 NVFP4 quantization-aware 4-step distilled models**; weights are available on HuggingFace: [Wan-NVFP4](https://huggingface.co/lightx2v/Wan-NVFP4).
 

README_zh.md

@@ -39,13 +39,13 @@ pre-commit run --all-files
 
 ## :fire: 最新动态
 
-- **2025年12月31日:** 🚀 我们Day0支持了[Qwen-Image-2512](https://huggingface.co/Qwen/Qwen-Image-2512) 文生图模型. 我们的[HuggingFace](https://huggingface.co/lightx2v/Qwen-Image-2512-Lightning) 已经更新了CFG/步数蒸馏lora权重。
+- **2025年12月31日:** 🚀 我们Day0支持了[Qwen-Image-2512](https://huggingface.co/Qwen/Qwen-Image-2512) 文生图模型. 我们的[HuggingFace](https://huggingface.co/lightx2v/Qwen-Image-2512-Lightning) 已经更新了CFG/步数蒸馏lora权重。使用方式可以参考[这里](https://github.com/ModelTC/LightX2V/tree/main/examples/qwen_image)。
 
 - **2025年12月27日:** 🚀 支持摩尔线程 MUSA 的部署。
 
 - **2025年12月25日:** 🚀 支持 AMD ROCm 和 Ascend 910B 的部署。
 
-- **2025年12月23日:** 🚀 我们Day0支持了[Qwen/Qwen-Image-Edit-2511](https://huggingface.co/Qwen/Qwen-Image-Edit-2511)的图像编辑模型，H100单卡，LightX2V可带来约1.4倍的速度提升，支持CFG并行/Ulysses并行，高效Offload等技术。我们的[HuggingFace](https://huggingface.co/lightx2v/Qwen-Image-Edit-2511-Lightning)已经更新了CFG/步数蒸馏lora和FP8权重。使用方式可以参考[Python脚本](https://github.com/ModelTC/LightX2V/tree/main/examples/qwen_image)。结合LightX2V，4步CFG/步数蒸馏，FP8模型，最高可以加速约42倍。可以在[LightX2V 在线服务](https://x2v.light-ai.top/login)的图生图的Qwen-Image-Edit-2511进行体验。
+- **2025年12月23日:** 🚀 我们Day0支持了[Qwen/Qwen-Image-Edit-2511](https://huggingface.co/Qwen/Qwen-Image-Edit-2511)的图像编辑模型，H100单卡，LightX2V可带来约1.4倍的速度提升，支持CFG并行/Ulysses并行，高效Offload等技术。我们的[HuggingFace](https://huggingface.co/lightx2v/Qwen-Image-Edit-2511-Lightning)已经更新了CFG/步数蒸馏lora和FP8权重。使用方式可以参考[这里](https://github.com/ModelTC/LightX2V/tree/main/examples/qwen_image)。结合LightX2V，4步CFG/步数蒸馏，FP8模型，最高可以加速约42倍。可以在[LightX2V 在线服务](https://x2v.light-ai.top/login)的图生图的Qwen-Image-Edit-2511进行体验。
 
 - **2025年12月22日:** 🚀 新增 **Wan2.1 NVFP4 量化感知 4 步蒸馏模型** 支持；模型与权重已发布在 HuggingFace： [Wan-NVFP4](https://huggingface.co/lightx2v/Wan-NVFP4)。