base_model:
- deepseek-ai/Janus-Pro-7B
license: apache-2.0
pipeline_tag: text-to-image
library_name: transformers
🌟🔥 T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
Official checkpoint for the paper "T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT".
Abstract
Recent advancements in large language models have demonstrated how chain-of-thought (CoT) and reinforcement learning (RL) can improve performance. However, applying such reasoning strategies to the visual generation domain remains largely unexplored. In this paper, we present T2I-R1, a novel reasoning-enhanced text-to-image generation model, powered by RL with a bi-level CoT reasoning process. Specifically, we identify two levels of CoT that can be utilized to enhance different stages of generation: (1) the semantic-level CoT for high-level planning of the prompt and (2) the token-level CoT for low-level pixel processing during patch-by-patch generation. To better coordinate these two levels of CoT, we introduce BiCoT-GRPO with an ensemble of generation rewards, which seamlessly optimizes both generation CoTs within the same training step. By applying our reasoning strategies to the baseline model, Janus-Pro, we achieve superior performance with 13% improvement on T2I-CompBench and 19% improvement on the WISE benchmark, even surpassing the state-of-the-art model FLUX.1. Code is available at: this https URL
Code: https://github.com/CaraJ7/T2I-R1
Usage
Please refer to the instructions in GitHub to set up the repository first then run the inference script below.
cd t2i-r1/src/infer
python reason_inference.py \
--model_path YOUR_MODEL_CKPT \
--data_path test_data.txt