Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,15 @@ library_name: diffusers
|
|
| 18 |
|
| 19 |
# VIBE: Visual Instruction Based Editor
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
**VIBE** is a powerful open-source framework for text-guided image editing. It leverages the efficiency of the [Sana1.5-1.6B](github.com/NVlabs/Sana) diffusion model and the visual understanding capabilities of [Qwen3-VL-2B-Instruct](github.com/QwenLM/Qwen3-VL) to provide **exceptionally fast** and high-quality, instruction-based image manipulation.
|
| 22 |
|
| 23 |
## Model Details
|
|
|
|
| 18 |
|
| 19 |
# VIBE: Visual Instruction Based Editor
|
| 20 |
|
| 21 |
+
<p style="text-align: center;">
|
| 22 |
+
<div align="center">
|
| 23 |
+
</div>
|
| 24 |
+
<p align="center">
|
| 25 |
+
<a href=""> 🌐 Project Page </a> |
|
| 26 |
+
<a href=""> 📜 Paper on arXiv </a> |
|
| 27 |
+
<a href="https://github.com/ai-forever/vibe"> Github </a> |
|
| 28 |
+
</p>
|
| 29 |
+
|
| 30 |
**VIBE** is a powerful open-source framework for text-guided image editing. It leverages the efficiency of the [Sana1.5-1.6B](github.com/NVlabs/Sana) diffusion model and the visual understanding capabilities of [Qwen3-VL-2B-Instruct](github.com/QwenLM/Qwen3-VL) to provide **exceptionally fast** and high-quality, instruction-based image manipulation.
|
| 31 |
|
| 32 |
## Model Details
|