Mini-DALLE3

Mini-DALLE3 copied to clipboard

Technical Report • Project page • Demo (Temporarily Unavailable)

https://github.com/Zeqiang-Lai/Mini-DALLE3/assets/26198430/5b6c0a0c-ebbf-48db-981e-f97d542a38b4

An experimental attempt to obtain the interactive and interleave text-to-image and text-to-text experience of DALL•E 3 and ChatGPT.

Try Yourself 🤗

• Download the checkpoint and save it as following

checkpoints
   - models
   - sdxl_models

• run the following commands, and you will get a gradio-based web demo.

export OPENAI_API_KEY="your key"
python -m minidalle3.web 

• To use other LLM rather than ChatGPT, such as baichuan.

python -m minidalle3.llm.baichuan
export OPENAI_API_BASE="http://0.0.0.0:10039/v1"
python -m minidalle3.web

chatglm, baichuan, internlm are tested. llama have not supported yet. qwen is not tested.

TODO

• [x] Support generating image interleaved in the conversations.
• [ ] Support generating multiple images at once.
• [ ] Support selecting image.
• [ ] Support refinement.
• [ ] Support prompt refinement/variation.
• [ ] Instruct tuned LLM/SD.

Citation

If you find this repo helpful, please consider citing us.

@misc{minidalle3,
    author={Lai, Zeqiang and Zhu, Xizhou and Dai, Jifeng and Qiao, Yu and Wang, Wenhai},
    title={Mini-DALLE3: Interactive Text to Image by Prompting Large Language Models},
    year={2023},
    url={https://github.com/Zeqiang-Lai/Mini-DALLE3},
}

Acknowledgement

IP-Adapter • Stable Diffusion XL