VARGPT V1.1

🚀 VARGPT-v1.1

Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning

VARGPT-v1.1 (7B+2B) models understanding and generation as two distinct paradigms within a unified model: predicting the next token for visual understanding and predicting the next scale for visual generation.

We provide a simple generation process for using our model. For more details, you can refer to VARGPT-v1.1 on Github.

🚀 Quick Start

The project provides a simple generation process for using the model. For more details, please refer to the GitHub repository.

✨ Features

• Multimodal Understanding: Capable of understanding multimodal data, such as images and text.
• Multimodal Generation: Can generate images based on text prompts.

💻 Usage Examples

Basic Usage - Multimodal Understanding

# Or execute the following code
import requests
from PIL import Image
import torch
from transformers import AutoProcessor, AutoTokenizer
from vargpt_qwen_v1_1.modeling_vargpt_qwen2_vl import VARGPTQwen2VLForConditionalGeneration
from vargpt_qwen_v1_1.prepare_vargpt_v1_1 import prepare_vargpt_qwen2vl_v1_1 
from vargpt_qwen_v1_1.processing_vargpt_qwen2_vl import VARGPTQwen2VLProcessor
from patching_utils.patching import patching

model_id = "VARGPT-family/VARGPT-v1.1"

prepare_vargpt_qwen2vl_v1_1(model_id)

model = VARGPTQwen2VLForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float32, 
    low_cpu_mem_usage=True, 
).to(0)

patching(model)

tokenizer = AutoTokenizer.from_pretrained(model_id)
processor = VARGPTQwen2VLProcessor.from_pretrained(model_id)

# Define a chat history and use `apply_chat_template` to get correctly formatted prompt
# Each value in "content" has to be a list of dicts with types ("text", "image") 
conversation = [
    {
      "role": "user",
      "content": [
          {"type": "text", "text": "Please explain the meme in detail."},
          {"type": "image"},
        ],
    },
]
prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
image_file = "./assets/llava_bench_demo.png"
print(prompt)

raw_image = Image.open(image_file)
inputs = processor(images=[raw_image], text=prompt, return_tensors='pt').to(0, torch.float32)

output = model.generate(
    **inputs, 
    max_new_tokens=2048, 
    do_sample=False)

print(processor.decode(output[0], skip_special_tokens=True))

Advanced Usage - Multimodal Generation

import requests
from PIL import Image
import torch
from transformers import AutoProcessor, AutoTokenizer
from vargpt_qwen_v1_1.modeling_vargpt_qwen2_vl import VARGPTQwen2VLForConditionalGeneration
from vargpt_qwen_v1_1.prepare_vargpt_v1_1 import prepare_vargpt_qwen2vl_v1_1 
from vargpt_qwen_v1_1.processing_vargpt_qwen2_vl import VARGPTQwen2VLProcessor
from patching_utils.patching import patching
model_id = "VARGPT-family/VARGPT-v1.1"

prepare_vargpt_qwen2vl_v1_1(model_id)

model = VARGPTQwen2VLForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float32,     
    low_cpu_mem_usage=True, 
).to(0)

patching(model)
tokenizer = AutoTokenizer.from_pretrained(model_id)
processor = VARGPTQwen2VLProcessor.from_pretrained(model_id)

conversation = [
    {
      "role": "user",
      "content": [
          {"type": "text", "text": "Can you depict a scene of A power metalalbum cover featuring a fantasy-style illustration witha white falcon."},
        ],
    },
]
prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
print(prompt)

inputs = processor(text=prompt, return_tensors='pt').to(0, torch.float32)
model._IMAGE_GEN_PATH = "output.png"
output = model.generate(
    **inputs, 
    max_new_tokens=4096, 
    do_sample=False)

print(processor.decode(output[0][:-1], skip_special_tokens=True))

📚 Documentation

The project uses the transformers library. The following is some basic information about the model:

📄 License

This project is licensed under the Apache-2.0 license.

📖 Citation

To cite the datasets and model, please use the following BibTeX entries:

@misc{zhuang2025vargptunifiedunderstandinggeneration,
      title={VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model}, 
      author={Xianwei Zhuang and Yuxin Xie and Yufan Deng and Liming Liang and Jinghan Ru and Yuguo Yin and Yuexian Zou},
      year={2025},
      eprint={2501.12327},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2501.12327}, 
}
@misc{zhuang2025vargptv11improvevisualautoregressive,
      title={VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning}, 
      author={Xianwei Zhuang and Yuxin Xie and Yufan Deng and Dongchao Yang and Liming Liang and Jinghan Ru and Yuguo Yin and Yuexian Zou},
      year={2025},
      eprint={2504.02949},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2504.02949}, 
}