README: switch to English (user request)

README.md

@@ -23,18 +23,16 @@ tags:
 
 # LTX-2.5-QuantFunc-4bit
 
-**4-bit 量化版 [Lightricks LTX-2.5](https://huggingface.co/Lightricks/LTX-2.5) 22B distilled —— 纯 4-bit 推理下画质对标 BF16,显存与权重体积降至约 1/3。** 由 [QuantFunc](https://github.com/quantfunc) 推理引擎量化与加载。
+**4-bit quantized [Lightricks LTX-2.5](https://huggingface.co/Lightricks/LTX-2.5) 22B distilled — pure 4-bit inference holds up to BF16 quality while cutting weight/VRAM footprint to roughly 1/3.** Quantized and loaded by the [QuantFunc](https://github.com/quantfunc) inference engine.
 
-## 为什么这个 4-bit 版本能保住画质 / Why pure 4-bit holds up
+## Why pure 4-bit holds up
 
-把一个 22B 视频/音频联合生成 DiT 压到 **4-bit 激活 × 4-bit 权重(纯 a4w4)**,最大的敌人是激活中的异常值(outliers)——它们撑爆 4-bit 的动态范围,直接表现为画面发糊、细节丢失。QuantFunc 在 SVDQuant 路线上做了两层关键创新:
+Compressing a 22B joint video/audio DiT down to **4-bit activations × 4-bit weights (pure a4w4)** runs into one main enemy: activation outliers, which blow past 4-bit's dynamic range and show up as blur and lost detail. QuantFunc adds two layers on top of the SVDQuant approach:
 
-1. **低秩分支吸收异常的能力被大幅增强。** 通过我们的算法创新,low-rank 分支能吸收比标准 SVDQuant 显著更多的激活异常能量——异常值在进入 4-bit 量化之前就被低秩通路"接走",主通路看到的分布干净得多。
-2. **残差被多种创新算法的组合进一步平滑。** 对低秩吸收后的残差,我们叠加了多种自研算法的组合处理,使残差中的异常值分布显著更平滑、更均匀——4-bit 网格因此能以更小的误差覆盖真实分布。
+1. **A much stronger low-rank branch.** Algorithmic improvements let the low-rank branch absorb significantly more activation-outlier energy than standard SVDQuant — outliers get siphoned off before the main path is quantized to 4-bit, so the main path sees a much cleaner distribution.
+2. **A smoother residual.** A combination of in-house techniques further smooths the outlier distribution in what's left after low-rank absorption, so the 4-bit grid covers the remaining distribution with far less error.
 
-两层叠加的结果:**纯 a4w4 推理下,输出视频(含音频)的清晰度、细节保持与运动连贯性对标 BF16 基线。**
-
-*In one line (EN): our enhanced low-rank branch absorbs substantially more activation-outlier energy than standard SVDQuant, and a combination of novel in-house techniques further smooths the outliers in the residual — so the 4-bit grid covers the remaining distribution with far less error. Net effect: clarity, detail retention and motion coherence on par with the BF16 baseline at roughly 1/3 the memory.*
+Net effect: **at pure a4w4 inference, output video (including audio) clarity, detail retention and motion coherence are on par with the BF16 baseline** — at roughly 1/3 the memory.
 
 ## Files
 
@@ -50,7 +48,7 @@ This is **not** a standard diffusers/safetensors checkpoint. The file is produce
 
 ## Inference settings (required for correct output)
 
-This is the **distilled** checkpoint, joint video+audio. It must be run with the distilled model's own schedule — using a generic/default scheduler will produce degraded output:
+This is the **distilled** checkpoint, joint video+audio. It must be run with the distilled model's own schedule — a generic/default scheduler will produce degraded output:
 
 - **Sigma schedule (8 steps, fixed):** `1.0, 0.99375, 0.9875, 0.98125, 0.975, 0.909375, 0.725, 0.421875, 0.0`
 - **CFG:** `1` (no classifier-free guidance — this is a guidance-distilled model)
@@ -66,11 +64,11 @@ This repository redistributes **derived (quantized) weights only**, produced fro
 
 ## License
 
-Follows the original model's **LTX-2 Community License Agreement** ([license text](https://github.com/Lightricks/LTX-2/blob/main/LICENSE))。本仓库仅分发量化权重;原始模型版权与许可归 Lightricks 所有。
+Follows the original model's **LTX-2 Community License Agreement** ([license text](https://github.com/Lightricks/LTX-2/blob/main/LICENSE)). This repository distributes quantized weights only; copyright and licensing of the original model belong to Lightricks.
 
-## 社区 / Community
+## Community
 
-- 🌐 [QuantFunc 官网](https://www.quantfunc.com/)
-- 🐙 [ComfyUI-QuantFunc GitHub](https://github.com/QuantFunc/ComfyUI-QuantFunc)
+- 🌐 [QuantFunc website](https://www.quantfunc.com/)
+- 🐙 [ComfyUI-QuantFunc on GitHub](https://github.com/QuantFunc/ComfyUI-QuantFunc)
 - 🤗 [Hugging Face](https://huggingface.co/QuantFunc)  |  🤖 [ModelScope](https://www.modelscope.cn/profile/QuantFunc)
-- 🎮 [Discord 服务器](https://discord.gg/jCp9TpFWcn)
+- 🎮 [Discord](https://discord.gg/jCp9TpFWcn)