DAMO-NLP-SG/DiGIT
[NeurIPS 2024] Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective
This project offers an advanced method for generating realistic and coherent images from scratch, or for better understanding the content of existing images. It takes raw image data and processes it to produce high-quality synthetic images or to extract meaningful insights about image features. This tool is ideal for researchers and practitioners in computer vision, generative AI, and digital media who need to create new images or improve image analysis capabilities.
No commits in the last 6 months.
Use this if you need to generate high-fidelity images for research or applications, or if you want to enhance the accuracy of image classification and understanding tasks.
Not ideal if your primary need is for video generation, 3D model creation, or if you require extremely low computational overhead for real-time applications on limited hardware.
Stars
79
Forks
1
Language
Python
License
MIT
Category
Last pushed
Oct 31, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/DAMO-NLP-SG/DiGIT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
zai-org/CogVideo
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
zhaorw02/DeepMesh
[ICCV 2025] Official code of DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
YangLing0818/RPG-DiffusionMaster
[ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with...
thu-nics/FrameFusion
[ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token...
Yushi-Hu/tifa
TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering