EleutherAI/DALLE-mtf
Open-AI's DALL-E for large scale training in mesh-tensorflow.
This project helps machine learning researchers and engineers train large-scale DALL-E models. It takes in collections of images and corresponding text captions to produce a custom DALL-E model. The primary users are those looking to experiment with or replicate state-of-the-art text-to-image generation at scale.
431 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher who needs to train a DALL-E-like model on your own large datasets, leveraging Google Cloud TPUs for distributed training.
Not ideal if you are looking for a pre-trained DALL-E model to use directly for image generation, or if you don't have access to or experience with Google Cloud Platform and TPUs.
Stars
431
Forks
45
Language
Python
License
MIT
Category
Last pushed
Feb 12, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/EleutherAI/DALLE-mtf"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
filipstrand/mflux
MLX native implementations of state-of-the-art generative image models
potamides/DeTikZify
Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ.
FoundationVision/Infinity
[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
zai-org/CogView
Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image...
Alpha-VLLM/Lumina-T2X
Lumina-T2X is a unified framework for Text to Any Modality Generation