docs: remove HSWQ references and correct ControlNet ConvRot INT8 model card

README.md

@@ -18,11 +18,7 @@ library_name: videox_fun
 
 # ControlNet Models (ConvRot INT8)
 
-<p align="center">
-  <img src="https://raw.githubusercontent.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization/main/icon.png" width="128">
-</p>
-
-High-fidelity **ConvRot INT8** quantized weights for diffusion ControlNet models. This repository provides memory-efficient, production-grade INT8 quantized checkpoints maintaining high structural fidelity and multi-condition guidance.
+High-fidelity **ConvRot INT8** quantized weights for diffusion ControlNet models. This repository provides memory-efficient INT8 quantized checkpoints maintaining high structural fidelity and multi-condition guidance.
 
 ---
 
@@ -30,18 +26,18 @@ High-fidelity **ConvRot INT8** quantized weights for diffusion ControlNet models
 
 This repository hosts the **ConvRot INT8** quantized edition of **`Qwen-Image-2512-Fun-Controlnet-Union-2602`**, originally developed and trained by **Alibaba PAI / VideoX-Fun**.
 
-The **ConvRot INT8** format applies rotational transformation matrix optimizations to eliminate outlier activation skew and ensure minimal reconstruction error, reducing the model footprint to **~1.64 GB** while preserving multi-condition structural precision.
+The **ConvRot INT8** format applies rotational transformation matrix optimizations to suppress outlier activations and minimize quantization error, reducing the model footprint to **~1.64 GB** (from ~3.3+ GB FP16) while preserving multi-condition structural precision.
 
 - **Base Model:** [alibaba-pai/Qwen-Image-2512-Fun-Controlnet-Union](https://huggingface.co/alibaba-pai/Qwen-Image-2512-Fun-Controlnet-Union)
 - **Architecture:** Multi-condition Union ControlNet added across 5 layer blocks of Qwen-Image-2512.
-- **Quantization:** Full ConvRot INT8 (weights stored as `int8_tensorwise` with rotation matrices).
+- **Quantization:** Full ConvRot INT8 (weights stored with rotational transformations).
 - **License:** Apache-2.0
 
 ---
 
 ## 📦 Available Models
 
-| Filename | Base Architecture | Supported Conditions | Quantization | Size | License |
+| Filename | Base Architecture | Supported Conditions | Precision | File Size | License |
 | :--- | :--- | :--- | :--- | :--- | :--- |
 | `Qwen-Image-2512-Fun-Controlnet-Union-2602_convrot_int8.safetensors` | Qwen-Image-2512 (5 Layer Blocks) | Canny, HED, Depth, Pose, MLSD, Scribble, Gray, Inpaint | ConvRot INT8 | ~1.64 GB | Apache-2.0 |
 
@@ -108,9 +104,7 @@ python examples/qwenimage_fun/predict_i2i_inpaint.py
 
 ### 2. ComfyUI
 
-For ComfyUI workflows, use the dedicated loader node pack:
-- **[ComfyUI-HSWQ-Loader-and-Tools](https://github.com/ussoewwin/ComfyUI-HSWQ-Loader-and-Tools)**
-- **[ComfyUI-QwenImageLoraLoader](https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader)**
+Compatible with ComfyUI environments supporting INT8 quantized ControlNet / VideoX-Fun models.
 
 ---