---
license: apache-2.0
base_model:
- ByteDance/Bernini-R
tags:
- text-to-video
- image-to-video
- video-to-video
- image-to-image
- audio-to-video
- wan-s2v
- bernini-r-s2v
---

# Bernini-R-S2V

<video controls width="100%" height="480">
  <source src="https://huggingface.co/rzgar/Bernini-R-S2V/resolve/main/Bernini-R-S2V-FP8/video/ComfyUI__00005-audio.mp4" type="video/mp4">
  Your browser does not support the video tag.
</video>

*Speech-driven video on Bernini-R , T2V, I2V, and V2V with lip-sync.*

This model adds single-speaker audio support to Bernini-R, so you can drive video with speech in text-to-video, image-to-video, and video-to-video setups. 
It is not state-of-the-art audio-to-video, but it removes the need for post-processing or extra models just to add speech to Wan videos. 
For basic talking-head work, or longer videos built from short sequences, it is a handy all-in-one option on top of Bernini's motion and editing strengths.


| File | Role |
|---|---|
| '[wan2.2_bernini_r_high_noise_fp16_s2v.safetensors](https://huggingface.co/rzgar/Bernini-R-S2V/resolve/main/Bernini-R-S2V-FP16/wan2.2_bernini_r_high_noise_fp16_s2v.safetensors)'| High noise |
| '[wan2.2_bernini_r_low_noise_fp16_s2v.safetensors](https://huggingface.co/rzgar/Bernini-R-S2V/resolve/main/Bernini-R-S2V-FP16/wan2.2_bernini_r_low_noise_fp16_s2v.safetensors)'| Low noise |
| '[wan2.2_bernini_r_high_noise_fp8_scaled_s2v.safetensors](https://huggingface.co/rzgar/Bernini-R-S2V/resolve/main/Bernini-R-S2V-FP8/wan2.2_bernini_r_high_noise_fp8_scaled_s2v.safetensors)' | High noise |
| '[wan2.2_bernini_r_low_noise_fp8_scaled_s2v.safetensors](https://huggingface.co/rzgar/Bernini-R-S2V/resolve/main/Bernini-R-S2V-FP8/wan2.2_bernini_r_low_noise_fp8_scaled_s2v.safetensors)' | Low noise |
| '[wan2.2_bernini_r_high_noise_int8_convrot_s2v.safetensors](https://huggingface.co/rzgar/Bernini-R-S2V/resolve/main/Bernini-R-S2V-int8-convrot/wan2.2_bernini_r_high_noise_int8_convrot_s2v.safetensors)' | High noise |
| '[wan2.2_bernini_r_low_noise_int8_convrot_s2v.safetensors](https://huggingface.co/rzgar/Bernini-R-S2V/resolve/main/Bernini-R-S2V-int8-convrot/wan2.2_bernini_r_low_noise_int8_convrot_s2v.safetensors)' | Low noise |

ComfyUI detects these as **`WAN22_S2V`** / 'WanModel_S2V' (audio keys trigger S2V model type).

## Usage

1. Download  the checkpoints.
2. Place in:
   ```
   ComfyUI/models/diffusion_models/
   ```
3. Add [wav2vec2](https://huggingface.co/rzgar/Bernini-R-S2V/resolve/main/audio_encoders/wav2vec2_large_english_fp16.safetensors) to: 
   ```
   ComfyUI/models/audio_encoders/
   ```
4. Install **[ComfyUI-WanBerniniS2V](https://huggingface.co/rzgar/Bernini-R-S2V/tree/main/ComfyUI-WanBerniniS2V)** custom node:
   ```
   (Create a folder in 'ComfyUI/custom_nodes/'  named 'ComfyUI-WanBerniniS2V', then save the Python files in that folder.)
   ```
5. Restart ComfyUI.
6. Search for the Bernini S2V Conditioning node or use the example [workfllow](https://huggingface.co/rzgar/Bernini-R-S2V/blob/main/Workflow/Bernini-R-S2V_Workflow.json)

## Audio tips

| Setting | Recommendation |
|---|---|
| **Channels** | **Mono**, wav2vec2 downmixes stereo internally |
| **Sample rate** | 44.1 khz or 48 khz (resampled to 16 kHz) |
| **Content** | Clear speech, less background music = better sync |
| **Length** | in my testing, max 9 to 15 seconds |