Hugging Face's logo

All Things ViTs

non-profit
https://all-things-vits.github.io/atv/
all-things-vits
Activity Feed

AI & ML interests

Hosts materials for CVPR 2023 tutorial: All Things ViTs: Understanding and Interpreting Attention in Vision.

Recent Activity

sayakpaul  authored a paper 20 days ago
A Noise is Worth Diffusion Guidance
sayakpaul  authored a paper 4 months ago
LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs
Hila  authored a paper 5 months ago
Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers
View all activity

all-things-vits's activity

sayakpaul 
posted an update 2 days ago
sayakpaul 
posted an update 8 days ago
view post
Post
1561
In the past seven days, the Diffusers team has shipped:

1. Two new video models
2. One new image model
3. Two new quantization backends
4. Three new fine-tuning scripts
5. Multiple fixes and library QoL improvements

Coffee on me if someone can guess 1 - 4 correctly.
  • 1 reply
·
sayakpaul 
posted an update 16 days ago
view post
Post
2041
Introducing a high-quality open-preference dataset to further this line of research for image generation.

Despite being such an inseparable component for modern image generation, open preference datasets are a rarity!

So, we decided to work on one with the community!

Check it out here:
https://huggingface.co/blog/image-preferences
·
sayakpaul 
posted an update 17 days ago
view post
Post
2096
The Control family of Flux from @black-forest-labs should be discussed more!

It enables structural controls like ControlNets while being significantly less expensive to run!

So, we're working on a Control LoRA training script 🤗

It's still WIP, so go easy:
https://github.com/huggingface/diffusers/pull/10130
sayakpaul 
authored a paper 20 days ago
sayakpaul 
posted an update 27 days ago
sayakpaul 
posted an update about 1 month ago
view post
Post
2602
It's been a while we shipped native quantization support in diffusers 🧨

We currently support bistandbytes as the official backend but using others like torchao is already very simple.

This post is just a reminder of what's possible:

1. Loading a model with a quantization config
2. Saving a model with quantization config
3. Loading a pre-quantized model
4. enable_model_cpu_offload()
5. Training and loading LoRAs into quantized checkpoints

Docs:
https://huggingface.co/docs/diffusers/main/en/quantization/bitsandbytes
  • 1 reply
·
sayakpaul 
posted an update 3 months ago
view post
Post
2752
Did some little experimentation to resize pre-trained LoRAs on Flux. I explored two themes:

* Decrease the rank of a LoRA
* Increase the rank of a LoRA

The first one is helpful in reducing memory requirements if the LoRA is of a high rank, while the second one is merely an experiment. Another implication of this study is in the unification of LoRA ranks when you would like to torch.compile() them.

Check it out here:
sayakpaul/flux-lora-resizing
  • 1 reply
·
sayakpaul 
authored a paper 4 months ago
sayakpaul 
posted an update 4 months ago
sayakpaul 
posted an update 5 months ago
view post
Post
4478
Flux.1-Dev like images but in fewer steps.

Merging code (very simple), inference code, merged params: sayakpaul/FLUX.1-merged

Enjoy the Monday 🤗
·
sayakpaul 
posted an update 5 months ago
view post
Post
3793
With larger and larger diffusion transformers coming up, it's becoming increasingly important to have some good quantization tools for them.

We present our findings from a series of experiments on quantizing different diffusion pipelines based on diffusion transformers.

We demonstrate excellent memory savings with a bit of sacrifice on inference latency which is expected to improve in the coming days.

Diffusers 🤝 Quanto ❤️

This was a juicy collaboration between @dacorvo and myself.

Check out the post to learn all about it
https://huggingface.co/blog/quanto-diffusers
·
Hila 
authored 2 papers 5 months ago
sayakpaul 
posted an update 6 months ago
sayakpaul 
posted an update 6 months ago
view post
Post
3131
What is your favorite part of our Diffusers integration of Stable Diffusion 3?

My personal favorite is the ability to run it on a variety of different GPUs with minimal code changes.

Learn more about them here:
https://huggingface.co/blog/sd3
sayakpaul 
authored a paper 7 months ago
sayakpaul 
posted an update 7 months ago
view post
Post
1866
🧨 Diffusers 0.28.0 is out 🔥

It features the first non-generative pipeline of the library -- Marigold 🥁

Marigold shines at performing Depth Estimation and Surface Normal Estimation. It was contributed by @toshas , one of the authors of Marigold.

This release also features a massive refactor (led by @DN6 ) of the from_single_file() method, highlighting our efforts for making our library more amenable to community features 🤗

Check out the release notes here:
https://github.com/huggingface/diffusers/releases/tag/v0.28.0
sayakpaul 
posted an update 8 months ago
view post
Post
2022
Custom pipelines and components in Diffusers 🎸

Wanted to use customized pipelines and other components (schedulers, unets, text encoders, etc.) in Diffusers?

Found it inflexible?

Since the first dawn on earth, we have supported loading custom pipelines via a custom_pipeline argument 🌄

These pipelines are inference-only, i.e., the assumption is that we're leveraging an existing checkpoint (e.g., runwayml/stable-diffusion-v1-5) and ONLY modifying the pipeline implementation.

We have many cool pipelines, implemented that way. They all share the same benefits available to a DiffusionPipeline, no compromise there 🤗

Check them here:
https://github.com/huggingface/diffusers/tree/main/examples/community

Then we might have a requirement of everything customized i.e., custom components along with a custom pipeline. Sure, that's all possible.

All you have to do is keep the implementations of those custom components on the Hub repository you're loading your pipeline checkpoint from.

SDXL Japanese was implemented like this 🔥
stabilityai/japanese-stable-diffusion-xl

Full guide is available here ⬇️
https://huggingface.co/docs/diffusers/main/en/using-diffusers/custom_pipeline_overview

And, of course, these share all the benefits that come with DiffusionPipeline.
sayakpaul 
posted an update 9 months ago