Image-to-Text
Transformers
Safetensors
English
qwen3_vl
image-text-to-text
text-to-image
image-to-image
edit
reasoning
reward
Instructions to use TIGER-Lab/RationalRewards-8B-T2I with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TIGER-Lab/RationalRewards-8B-T2I with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="TIGER-Lab/RationalRewards-8B-T2I")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("TIGER-Lab/RationalRewards-8B-T2I") model = AutoModelForImageTextToText.from_pretrained("TIGER-Lab/RationalRewards-8B-T2I") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,9 @@ tags:
|
|
| 18 |
- reward
|
| 19 |
---
|
| 20 |
|
|
|
|
|
|
|
|
|
|
| 21 |
# RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
|
| 22 |
|
| 23 |
<div align="left">
|
|
|
|
| 18 |
- reward
|
| 19 |
---
|
| 20 |
|
| 21 |
+
**TLDR:** this is a reasoning reward model that supports text-to-image generation, from the following paper.
|
| 22 |
+
|
| 23 |
+
---
|
| 24 |
# RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
|
| 25 |
|
| 26 |
<div align="left">
|