README.md

---
language:
- en
pipeline_tag: image-to-image
tags:
- image-editing
- text-guided-editing
- diffusion
- sana
- qwen-vl
- multimodal
- distilled
- cfg-distillation
base_model:
- iitolstykh/VIBE-Image-Edit
library_name: diffusers
---

# VIBE: Visual Instruction Based Editor

<div align="center">
  <img src="VIBE.png" width="800" alt="VIBE"/>
</div>

<p style="text-align: center;">
  <div align="center">
  </div>
  <p align="center">
  <a href="https://riko0.github.io/VIBE"> 🌐 Project Page </a> | 
  <a href="https://arxiv.org/abs/2601.02242"> 📜 Paper on arXiv </a> | 
  <a href="https://github.com/ai-forever/vibe"> Github </a> | 
  <a href="https://huggingface.co/spaces/iitolstykh/VIBE-Image-Edit-DEMO">🤗 Space | </a> 
  <a href="https://huggingface.co/iitolstykh/VIBE-Image-Edit">🤗 VIBE-Image-Edit | </a> 
</p>

**VIBE-DistilledCFG** is a specialized version of the original [VIBE-Image-Edit](https://huggingface.co/iitolstykh/VIBE-Image-Edit) model. 

This model can be run without classifier-free guidance, substantially reducing image generation time while maintaining high quality outputs.

## Performance Comparison

Below is a comparison of total inference time between the original VIBE model (using CFG) and this DistilledCFG model (without CFG). The distillation process yields an approx **1.8x - 2x speedup**.

| Resolution | Original Model (with CFG) | DistilledCFG Model (No CFG) |
| :--- | :--- | :--- |
| **1024x1024** | 1.1453s | **0.6389s** |
| **2048x2048** | 4.0837s | **1.9687s** |

## Model Details

- **Name:** VIBE-DistilledCFG
- **Parent Model:** [iitolstykh/VIBE-Image-Edit](https://huggingface.co/iitolstykh/VIBE-Image-Edit)
- **Task:** Text-Guided Image Editing
- **Architecture:**
  - **Diffusion Backbone:** Sana1.5 (1.6B parameters) with Linear Attention.
  - **Condition Encoder:** Qwen3-VL (2B parameters).
- **Technique:** Classifier-Free Guidance (CFG) Distillation.
- **Model precision**: torch.bfloat16 (BF16)
- **Model resolution**: Optimized for up to 2048px images.

## Features

- **Blazing Fast Inference:** Runs approximately 2x faster than the original model by skipping the guidance pass.
- **Text-Guided Editing:** Edit images using natural language instructions.
- **Compact & Efficient:** Retains the lightweight footprint of the original 1.6B/2B architecture.
- **Multimodal Understanding:** Powered by Qwen3-VL for precise instruction following.
- **Text-to-Image** support.

# Inference Requirements

- `vibe` library
```bash
pip install git+https://github.com/ai-forever/VIBE
```
- requirements for `vibe` library:
```bash
pip install transformers==4.57.1 torchvision==0.21.0 torch==2.6.0 diffusers==0.33.1 loguru==0.7.3
```

# Quick start

**Note:** When using this distilled model, please set `image_guidance_scale` and `guidance_scale` to 0.0 to disable CFG.

```python
from PIL import Image
import requests
from io import BytesIO
from huggingface_hub import snapshot_download

from vibe.editor import ImageEditor

# Download model
model_path = snapshot_download(
    repo_id="iitolstykh/VIBE-Image-Edit-DistilledCFG",
    repo_type="model",
)

# Load model
# Note: Guidance scales are removed for the distilled version
editor = ImageEditor(
    checkpoint_path=model_path,
    num_inference_steps=20,
    image_guidance_scale=0.0,
    guidance_scale=0.0,
    device="cuda:0",
)

# Download test image
resp = requests.get('https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3f58a82a-b4b4-40c3-a318-43f9350fcd02/original=true,quality=90/115610275.jpeg')
image = Image.open(BytesIO(resp.content))

# Generate edited image
edited_image = editor.generate_edited_image(
    instruction="let this case swim in the river",
    conditioning_image=image,
    num_images_per_prompt=1,
)[0]

edited_image.save(f"edited_image.jpg", quality=100)
```

## License

This project is built upon the SANA. Please refer to the original SANA license for usage terms:
[SANA License](https://huggingface.co/Efficient-Large-Model/SANA1.5_4.8B_1024px_diffusers/blob/main/LICENSE.txt)

## Citation

If you use this model in your research or applications, please acknowledge the original projects:

- [SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer](https://github.com/NVlabs/Sana)
- [Qwen3-VL](https://github.com/QwenLM/Qwen3-VL)

```bibtex
@misc{vibe2026,
  Author = {Grigorii Alekseenko and Aleksandr Gordeev and Irina Tolstykh and Bulat Suleimanov and Vladimir Dokholyan and Georgii Fedorov and Sergey Yakubson and Aleksandra Tsybina and Mikhail Chernyshov and Maksim Kuprashevich},
  Title = {VIBE: Visual Instruction Based Editor},
  Year = {2026},
  Eprint = {arXiv:2601.02242},
}
```