Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
| Date | Stars |
|---|---|
| 2026-07-24 | 8417 |
| 2026-07-25 | 8417 |
| 2026-07-28 | 8417 |
| 2026-07-30 | 8417 |
| 2026-07-31 | 8416 |
| 2026-08-04 | 8416 |
| 2026-08-06 | 8416 |
Today
— stars today
This week
-1 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<img src="./imagen.png" width="450px"></img> ## Imagen - Pytorch Implementation of <a href="https://gweb-research-imagen.appspot.com/">Imagen</a>, Google's Text-to-Image Neural Network that beats DALL-E2, in Pytorch. It is the new SOTA for text-to-image synthesis. Architecturally, it is actually much simpler than DALL-E2. It consists of a cascading DDPM conditioned on text embeddings from a large pretrained T5 model (attention network). It also contains dynamic clipping for improved classifier free guidance, noise level conditioning, and a memory efficient unet design. It appears neither CLIP nor prior network is needed after all. And so research continues. <a href="https://www.youtube.com/watch?v=xqDeAz0U-R4">AI Coffee Break with Letitia</a> | <a href="https://www.assemblyai.com/blog/how-imagen-actually-works/">Assembly AI</a> | <a href="https://www.youtube.com/watch?v=af6WPqvzjjk">Yannic Kilcher</a> Please join <a href="https://discord.gg/xBPBXfcFHd"><img alt="Join us on Discord" src="https://img.shields.io/discord/823813159592001537?color=5865F2&logo=discord&logoColor=white"></a> if you are interested in helping out with the replication with the <a href="https://laion.ai/">LAION</a> community ## Shoutouts - <a href="https://stability.ai/">StabilityAI</a> for the generous sponsorship, as well as my other sponsors out there - <a href="https://huggingface.co/">🤗 Huggingface</a> for their amazing transformers library. The text encoder portion is pretty much taken care of because of them - <a href="http://www.jonathanho.me/">Jonathan Ho</a> for bringing about a revolution in generative artificial intelligence through <a href="https://arxiv.org/abs/2006.11239">his seminal paper</a> - <a href="https://github.com/sgugger">Sylvain</a> and <a href="https://github.com/muellerzr">Zachary</a> for the <a href="https://github.com/huggingface/accelerate">Accelerate</a> library, which this repository uses for distributed training - <a href="https://github.com/arogozhnikov">Alex</a> for <a href="https://github.com/arogozhnikov/einops">einops</a>, indispensable tool for tensor manipulation - <a href="https://github.com/jorgemcgomes">Jorge Gomes</a> for helping out with the T5 loading code and advice on the correct T5 version - <a href="https://github.com/crowsonkb">Katherine Crowson</a>, for her <a href="https://github.com/crowsonkb/v-diffusion-jax/blob/master/diffusion/utils.py">beautiful code</a>, which helped me understand the continuous time version of gaussian diffusion - <a href="https://github.com/marunine">Marunine</a> and <a href="https://github.com/Netruk44">Netruk44</a>, for reviewing code, sharing experimental results, and help with debugging - <a href="https://github.com/marunine">Marunine</a> for providing a <a href="https://github.com/lucidrains/imagen-pytorch/issues/72#issuecomment-1163275757">potential solution</a> for a color shifting issue in the memory efficient u-nets. Thanks to <a href="https://github.com/jacobwjs">Jacob</a> for sharing experimental comparisons between the base and memory-efficient unets - <a href="https://github.com/marunine">Marunine</a> for finding numerous bugs, resolving an issue with resize right, and for sharing his experimental configurations and results - <a href="https://github.com/MalumaDev">MalumaDev</a> for proposing the use of pixel shuffle upsampler to fix checkboard artifacts - <a href="https://github.com/KhrulkovV">Valentin</a> for pointing out insufficient skip connections in the unet, as well as the specific method of attention conditioning in the base-unet in the appendix - <a href="https://github.com/BIGJUN777">BIGJUN</a> for catching a big bug with continuous time gaussian diffusion noise level conditioning at inference time - <a href="https://github.com/animebing">Bingbing</a> for identifying a bug with sampling and order of normalizing and noising with low resolution conditioning image - <a href="https://github.com/TheFusion21">Kay</a> for contributing one li
Excerpt of 39,644 characters
Read on GitHub
Phil Wang · United States
485
Daniel Perry
8
6
5
3
2
1
1
1
1
1
1
1
Ryan Russell
1
1
some financial technology company · United Kingdom
1
1
1
Perry Gibson · fractile.ai
1
Victor Fragoso · Microsoft · United States
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8622394762cbbbfd, topic:text-to-image, desc:text-to-image, readme:text-to-image
matched fp:8622394762cbbbfd, topic:deep-learning, readme:distributed training
matched fp:8622394762cbbbfd, topic:text-to-video