Fix usage instructions: correct model class / plugin guidance, English-only

README.md

@@ -7,26 +7,34 @@ tags:
 - camera-movement
 - video-understanding
 - qwen3-vl
-- sft
 - vggt-injection
 ---
 
 # CamInject-4B
 
-This repository contains the **CamInject-4B** model from the paper [Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation](https://huggingface.co/papers/2608.10932).
+Camera-movement understanding model that **injects frozen VGGT camera tokens** into
+`Qwen/Qwen3-VL-4B-Instruct`. Given a video, it outputs structured JSON describing every
+camera-movement segment.
 
-**Project page**: https://ddz16.github.io/cammotion.github.io  
-**GitHub**: https://github.com/ddz16/CamDistill
+- **Paper**: [Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation](https://huggingface.co/papers/2608.10932)
+- **Project page**: https://ddz16.github.io/cammotion.github.io
+- **Code**: https://github.com/ddz16/CamDistill
 
-Camera-movement VGGT-Direct 注入 SFT 微调模型，基于 `Qwen/Qwen3-VL-4B-Instruct`。
+> ⚠️ **This model cannot be loaded with plain 🤗 Transformers.** It requires a custom model type
+> (registered via a plugin) **and** runs VGGT online to produce camera tokens. Loading it as a
+> standard `Qwen3VLForConditionalGeneration` would not work correctly. Use the CamDistill repo.
 
-- Checkpoint: `checkpoint-1326`
-- 训练框架: [ms-swift](https://github.com/modelscope/ms-swift)
+## Usage
 
-## 使用
+Clone the [CamDistill repo](https://github.com/ddz16/CamDistill) and clone VGGT-Omega (set `VGGT_OMEGA_REPO`, see the repo's
+setup). CamInject runs VGGT online during inference:
 
-```python
-from transformers import AutoModelForCausalLM, AutoProcessor
-model = AutoModelForCausalLM.from_pretrained("ddz16/CamInject-4B", torch_dtype="bfloat16", device_map="auto")
-processor = AutoProcessor.from_pretrained("ddz16/CamInject-4B")
-```
+```bash
+VGGT_TEACHER_TYPE=vggt_omega \
+python camera_movement_sft/infer_single.py \
+    --model ddz16/CamInject-4B \
+    --video /path/to/video.mp4 \
+    --variant caminject
+```
+
+See the repo's README for environment setup and batch evaluation.