xin-ic sayak-hf

university

AI & ML interests

3D diffusion

Recent Activity

Xin-Sayak's activity

sayakpaulΒ 
posted an update 1 day ago
view post
Post
2388
Commits speak louder than words πŸ€ͺ

* 4 new video models
* Multiple image models, including SANA & Flux Control
* New quantizers -> GGUF & TorchAO
* New training scripts

Enjoy this holiday-special Diffusers release πŸ€—
Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0
sayakpaulΒ 
posted an update 8 days ago
view post
Post
1552
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
Β·
sayakpaulΒ 
posted an update 16 days ago
view post
Post
2040
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
Β·
sayakpaulΒ 
posted an update 16 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 πŸ€—

It's still WIP, so go easy:
https://github.com/huggingface/diffusers/pull/10130
sayakpaulΒ 
posted an update 26 days ago
sayakpaulΒ 
posted an update about 1 month ago
view post
Post
2601
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
Β·
sayakpaulΒ 
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
Β·
sayakpaulΒ 
posted an update 4 months ago
sayakpaulΒ 
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 πŸ€—
Β·
sayakpaulΒ 
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
Β·
sayakpaulΒ 
posted an update 6 months ago
sayakpaulΒ 
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
sayakpaulΒ 
posted an update 7 months ago
view post
Post
1866
🧨 Diffusers 0.28.0 is out πŸ”₯

It features the first non-generative pipeline of the library -- Marigold πŸ₯

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 πŸ€—

Check out the release notes here:
https://github.com/huggingface/diffusers/releases/tag/v0.28.0
sayakpaulΒ 
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 πŸŒ„

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 πŸ€—

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 πŸ”₯
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.
sayakpaulΒ 
posted an update 8 months ago
sayakpaulΒ 
posted an update 9 months ago
view post
Post
2386
Worked on a short blog post discussing how we semi-automated the release process of the diffusers library. The post delves deeper into the workflows responsible for:

* Publishing the package on Test PyPI and main PyPI servers.
* Notifying an internal Slack channel after a release is published on the repository.

Check it out here πŸ‘‰
https://sayak.dev/posts/streamlined-releases.html