picana/

Analogist

Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model. Zheng Gu, Shiyuan Yang, Jing Liao, Jing Huo, Yang Gao.

Project page All the image datasets can be achieved through this link. Please put them in a datasets folder. We also provide the GPT-4V prompts that we used in our experiments. Please see the *_gpt4_out.txt files. The data structure is as follows: Analogist ├── datasets │ ├── low_level_tasks_processed │ │ ├── ... │ │ ├── *_gpt4_out.txt │ ├──… See the full description on the dataset page: https://huggingface.co/datasets/picana/Analogist.