Update README.md
Browse files
README.md
CHANGED
|
@@ -33,6 +33,12 @@ This model is part of the work presented in the paper [RePlan: Reasoning-guided
|
|
| 33 |
|
| 34 |
<img src="assets/teaser.jpg">
|
| 35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
## Model Summary
|
| 37 |
|
| 38 |
This model is the **Planner module** of the **RePlan** framework, designed for complex instruction-based image editing. It is a fine-tuned version of **Qwen2.5-VL-7B**, trained with GRPO and only ~1k samples without any paired images.
|
|
|
|
| 33 |
|
| 34 |
<img src="assets/teaser.jpg">
|
| 35 |
|
| 36 |
+
Demo video of RePlan:
|
| 37 |
+
<div align="center">
|
| 38 |
+
<video src="https://cdn-uploads.huggingface.co/production/uploads/66e79b3c1c79fc2e51dc1d60/ctJTtc8IBQJ7aEq_vwEff.mp4" width="80%" controls></video>
|
| 39 |
+
</div>
|
| 40 |
+
|
| 41 |
+
|
| 42 |
## Model Summary
|
| 43 |
|
| 44 |
This model is the **Planner module** of the **RePlan** framework, designed for complex instruction-based image editing. It is a fine-tuned version of **Qwen2.5-VL-7B**, trained with GRPO and only ~1k samples without any paired images.
|