Update README.md

README.md

@@ -21,39 +21,44 @@ pipeline_tag: image-text-to-video
 
 ## 🎉 News
 
-- **[2026-06-10]** We open-sourced the inference code and model weights of the full Bernini (**Bernini**).
+- **[2026-06-11]** We open-sourced the inference code and model weights of the full Bernini (**Bernini**).
 - **[2026-05-22]** We released our paper [Bernini: Latent Semantic Planning for Video Diffusion](https://arxiv.org/abs/2605.22344).
 
 ## ✨ Highlights
 
 Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.
 
-Compared with the renderer-only Bernini-R release, **Bernini-Diffusers** packages the full semantic-planning pipeline: a Qwen2.5-VL planner, Bernini planning weights, and Wan2.2 diffusion components in one self-contained directory. This makes it the recommended release when you need stronger instruction following, multi-step semantic planning, and better handling of complex video editing requests.
+**Bernini-Diffusers-v2** packages the full semantic-planning pipeline: a Qwen2.5-VL planner, Bernini planning weights, and Wan2.2 diffusion components in one self-contained diffusers-format directory.
+
+Compared with the renderer-only Bernini-R releases, Bernini-Diffusers-v2 is recommended when you need stronger instruction following, multi-step semantic planning, and better handling of complex video generation or editing requests. Compared with the first Bernini-Diffusers release, v2 uses a training recipe that warms up the connector for thousands of steps before co-training, improving reference-guided video editing and OpenS2V performance.
 
 ## 🧾 Model card
 
 | Field | Description |
 |-------|-------------|
 | Model type | Full video generation/editing pipeline with an MLLM-based semantic planner and a DiT-based renderer. |
-| Checkpoint | [`ByteDance/Bernini-Diffusers`](https://huggingface.co/ByteDance/Bernini-Diffusers) |
+| Checkpoint | [`ByteDance/Bernini-Diffusers-v2`](https://huggingface.co/ByteDance/Bernini-Diffusers-v2) |
 | Code | [`ByteDance/Bernini`](https://github.com/bytedance/Bernini) |
+| Renderer base | [`Wan2.2-T2V-A14B`](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B) |
+| Planner base | [`Qwen2.5-VL-7B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) |
 | Recommended use | Complex generation/editing requests that benefit from explicit latent semantic planning and stronger instruction following. |
-| Model behavior | Better at decomposing complex instructions and planning semantic changes before rendering, at the cost of a heavier checkpoint layout than Bernini-R. |
+| Supported tasks | `t2i`, `i2i`, `t2v`, `v2v`, `rv2v`, and `r2v`. |
+| Model behavior | Decomposes complex instructions and plans semantic changes before rendering, at the cost of a heavier checkpoint layout than Bernini-R. |
 
 ### Benchmark snapshot
 
-| Model | EditVerse | OpenVE | OpenS2V | VBench | Bernini-v2v (OS) | Bernini-vr2v (OS) |
+| Model | EditVerse | OpenVE | OpenS2V | VBench | Bernini-v2v (OS) | Bernini-rv2v (OS) |
 |---|---|---|---|---|---|---|
-| [Bernini 7+14B](https://huggingface.co/ByteDance/Bernini-Diffusers) | 8.02 | 4.03 | 62.30 | 84.37 | 3.49 | 3.48 |
+| [Bernini-v2 7+14B](https://huggingface.co/ByteDance/Bernini-Diffusers-v2) | 8.02 | 3.96 | 63.83 | 84.46 | 3.49 | 3.55 |
 
 On video editing, Bernini reaches the first tier among leading closed-source commercial models in our internal arena evaluation based on blind human pairwise comparisons.
 
 ## 📦 Package layout
 
-This release is a **self-contained diffusers-format directory**. Pass the downloaded `Bernini-Diffusers` directory directly to `--config`.
+This release is a **self-contained diffusers-format directory**. Pass the downloaded `Bernini-Diffusers-v2` directory directly to `--config`.
 
 ```text
-Bernini-Diffusers/
+Bernini-Diffusers-v2/
   bernini/
   mllm/
   scheduler/
@@ -76,8 +81,8 @@ At runtime:
 
 ```bash
 pip install -U "huggingface_hub"
-hf download ByteDance/Bernini-Diffusers \
-    --local-dir pretrained_models/Bernini-Diffusers
+hf download ByteDance/Bernini-Diffusers-v2 \
+    --local-dir pretrained_models/Bernini-Diffusers-v2
 ```
 
 ## 🚀 Usage
@@ -89,27 +94,24 @@ The official inference code is available in the [Bernini repository](https://git
 ```bash
 git clone https://github.com/bytedance/Bernini.git bernini && cd bernini
 pip install -r requirements.txt
+# Open-VeOmni is required. Install it with --no-deps so it does not pull in a
+# different torch build and override the pinned torch==2.7.1+cu126:
+pip install --no-deps git+https://github.com/ByteDance-Seed/VeOmni.git@v0.1.11
 ```
 
 Recommended environment:
 
 - **Python** 3.11.2
-- **PyTorch** 2.5.1+cu124
-- **CUDA toolkit** 12.4
+- **PyTorch** 2.7.1+cu126
+- **CUDA toolkit** 12.6
 - **GPU** Hopper GPUs (H100/H800/H200) are recommended for best performance
 
-For multi-GPU sequence parallel inference, install VeOmni:
-
-```bash
-pip install --no-deps git+https://github.com/ByteDance-Seed/VeOmni.git@v0.1.10
-```
-
 ### Load the model
 
 Pass the downloaded directory directly as `--config`:
 
 ```bash
-python infer_single_gpu.py --config pretrained_models/Bernini-Diffusers \
+python infer_single_gpu.py --config pretrained_models/Bernini-Diffusers-v2 \
     --case assets/testcases/i2i/i2i.json --num_frames 1
 ```
 
@@ -127,17 +129,17 @@ export BERNINI_PE_MODEL=...        # vision-capable chat model
 
 ```bash
 # Single GPU
-python gradio_demo.py --config pretrained_models/Bernini-Diffusers --port 7860
+python gradio_demo.py --config pretrained_models/Bernini-Diffusers-v2 --port 7860
 
 # 8 GPUs, 8-way Ulysses sequence parallel
 torchrun --nproc-per-node 8 gradio_demo.py --ulysses 8 \
-    --config pretrained_models/Bernini-Diffusers \
+    --config pretrained_models/Bernini-Diffusers-v2 \
     --port 7860 --share
 ```
 
 ### Run scripts
 
-The [`scripts/bernini/`](https://github.com/bytedance/Bernini/tree/master/scripts/bernini) directory in the Bernini repo provides ready-to-run task launchers for the full pipeline:
+The [`scripts/bernini_v2/`](https://github.com/bytedance/Bernini/tree/master/scripts/bernini_v2) directory in the Bernini repo provides ready-to-run task launchers for Bernini-Diffusers-v2:
 
 - `run_t2i.sh`
 - `run_i2i.sh`
@@ -150,7 +152,7 @@ The [`scripts/bernini/`](https://github.com/bytedance/Bernini/tree/master/script
 You can override the model directory with:
 
 ```bash
-export BERNINI_CONFIG=/path/to/Bernini-Diffusers
+export BERNINI_CONFIG=/path/to/Bernini-Diffusers-v2
 ```
 
 ## 📑 Citation
@@ -177,6 +179,3 @@ Bernini builds on several outstanding open-source projects:
 ## 📄 License
 
 Apache License 2.0.
-
-
-hf upload TrizZZZZ/tmp /mnt/bn/editing/sunmingzhen.triz/codes/debug/Bernini/pretrained_models/Bernini-Diffusers