fnzhan / generative-ai Goto Github PK

Thank you for your nice survey! It really gives good guidance for the community.
However, we notice that in Table 1, the modality of scene graph in COCO is ticked. May I ask where is the COCO scene graph comes from? Actually, our recent work PSG provides a high-quality scene graph annotation based on COCO panoptic segmentation, so that Semantic Map, Bounding Box, Text, Scene Graph are all available in the PSG dataset.

You could get the general idea of PSG dataset by glancing our codebase or interactively explore the dataset on our website.
We would really appreciate if the PSG dataset could be included in the table and contribute to the image editing community.

Katherine Crowson, v-objective-diffusion.
https://github.com/crowsonkb/v-diffusion-pytorch

High-Resolution Image Synthesis with Latent Diffusion Models
Robin Rombach*, Andreas Blattmann*, Dominik Lorenz, Patrick Esser, Björn Ommer
* denotes equal contribution
https://github.com/CompVis/latent-diffusion
https://arxiv.org/abs/2112.10752

ruDALL-E
https://github.com/sberbank-ai/ru-dalle
https://rudalle.ru/en/

Russian Diffusion On Language Picture Hyper-modality RuDOLPH
A smaller ruDALL-E that makes use of parameter sharing. (Very new, can't find a paper)
https://github.com/sberbank-ai/ru-dolph

Paper for Emojich, which I believe is the associated research with ruDALL-E.
https://arxiv.org/pdf/2112.02448.pdf