imagen-pytorch
metaseq
imagen-pytorch | metaseq | |
---|---|---|
47 | 53 | |
7,787 | 6,389 | |
- | 0.4% | |
6.8 | 6.2 | |
about 1 month ago | 9 days ago | |
Python | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
imagen-pytorch
-
Google's StyleDrop can transfer style from a single image
If google doesnt, someone like lucidrains probably would implement it, just like he did for imagen and muse.
- Create a Stable diffusion neural network from scratch.
-
Google just announced an Even better diffusion process.
lucidrains/imagen-pytorch: Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch (github.com)
- Karlo, the first large scale open source DALL-E 2 replication is here
-
training imagen
Hi Can someone guide me a little, as to how i can use LAION dataset to train my imagen model? like how i can download the data, and in which format it should be fed to https://github.com/lucidrains/imagen-pytorch code?
-
If everyone in this sub make a donation of $10 then we can train truly open stable diffusion.
If we were to put money into training something, I'd hope we use a better model, like Imagen.
- AI Content Generation, Part 1: Machine Learning Basics
-
DALL-E 2 is switching to a credits system (50 generations for free at first, 15 free per month)
I've been messing around with this open-source implementation. You can get a pretty good idea of the model size by just copying the parameters from the paper.
-
Protests erupt outside of DALL-E offices after pricing implementation, press photograph
I'm waiting on this implementation/training of imagen: https://github.com/lucidrains/imagen-pytorch
-
Show HN: Food Does Not Exist
I'm honestly surprised that they trained a StyleGAN. Recently, the Imagen architecture has been show to be both easier in structure, easier to train, and even faster to produce good results. Combined with the "Elucidating" paper by NVIDIA's Tero Karras you can train a 256px Imagen to tolerable quality within an hour on a RTX 3090.
Here's a PyTorch implementation by the LAION people:
https://github.com/lucidrains/imagen-pytorch
And here's 2 images I sampled after training it for some hours, like 2 hours base model + 4 hours upscaler:
https://imgur.com/a/46EZsJo
metaseq
-
Training great LLMs from ground zero in the wilderness as a startup
This is a super important issue that affects the pace and breadth of iteration of AI almost as much as the raw hardware improvements do. The blog is fun but somewhat shallow and not technical or very surprising if you’ve worked with clusters of GPUs in any capacity over the years. (I liked the perspective of a former googler, but I’m not sure why past colleagues would recommend Jax over pytorch for LLMs outside of Google.) I hope this newco eventually releases a more technical report about their training adventures, like the PDF file here: https://github.com/facebookresearch/metaseq/tree/main/projec...
- Chronicles of Opt Development
-
See the pitch memo that raised €105M for four-week-old startup Mistral
The number of people who can actually pre-train a true LLM is very small.
It remains a major feat with many tweaks and tricks. Case in point: the 114 pages of OPT175B logbook [1]
[1] https://github.com/facebookresearch/metaseq/blob/main/projec...
- Technologie: „Austro-ChatGPT“ – aber kein Geld zum Testen
- OPT (Open Pre-trained Transformers) is a family of NLP models trained on billions of tokens of text obtained from the internet
- Current state-of-the-art open source LLM
-
Elon Musk Buys Ten Thousand GPUs for Secretive AI Project
Reliability at scale: take a look at the OPT training log book for their 175B model run. It needed a lot of babysitting. In my experience, that scale of TPU training run requires a restart about once every 1-2 weeks—and they provide the middleware to monitor the health of the cluster and pick up on hardware failures.
-
Is AI Development more fun than Software Development?
I really appreciated this log of Facebook training a large language model of how troublesome AI development can be: https://github.com/facebookresearch/metaseq/tree/main/projects/OPT/chronicles
-
Visual ChatGPT
Stable Diffusion will run on any decent gaming GPU or a modern MacBook, meanwhile LLMs comparable to GPT-3/ChatGPT have had pretty insane memory requirements - e.g., <https://github.com/facebookresearch/metaseq/issues/146>
-
Ask HN: Is There On-Call in ML?
It seems so, check this log book from Meta: https://github.com/facebookresearch/metaseq/blob/main/projec...
What are some alternatives?
dalle-mini - DALL·E Mini - Generate images from a text prompt
stable-diffusion - A latent text-to-image diffusion model
DALLE2-pytorch - Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
nlp-resume-parser - NLP-powered, GPT-3 enabled Resume Parser from PDF to JSON.
DALLE-pytorch - Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
GLM-130B - GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
latent-diffusion - High-Resolution Image Synthesis with Latent Diffusion Models
gpt-2 - Code for the paper "Language Models are Unsupervised Multitask Learners"
DeepCreamPy - deeppomf's DeepCreamPy + some updates
manim - Animation engine for explanatory math videos
CogVideo - Text-to-video generation. The repo for ICLR2023 paper "CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers"
cupscale - Image Upscaling GUI based on ESRGAN