Hugging Face's logo
Sayak Paul's picture
TFLOPS icon 13.5 TFLOPS
340 21 155

Sayak Paul

sayakpaul
grv805's profile picture lavieenrosesmz's profile picture Damanvohra66's profile picture
·
https://sayak.dev

AI & ML interests

Diffusion models, representation learning

Recent Activity

New activity about 21 hours ago
sayakpaul/mochi-lora:The uploaded videos are completely broken.
upvoted an article 1 day ago
Let’s make a generation of amazing image generation models
New activity 1 day ago
Spawning/PD12M:Okay to host the downloaded images?
View all activity

Articles

Organizations

Hugging Face's profile picture Deprem Private's profile picture 🧨Diffusers's profile picture TensorFlow TPU's profile picture Hugging Face Internal Testing Organization's profile picture ControlNet 1.1 Preview's profile picture Keras's profile picture All Things ViTs's profile picture Carted's profile picture Amazon ML's profile picture Instruction-tuned Diffusion Models's profile picture Probing ViTs's profile picture Evaluation on the Hub's profile picture JAX ♥️ Diffusers 🧨's profile picture (De)fusing's profile picture Huggingface Projects's profile picture Keras Dreambooth Event's profile picture Hugging Face OSS Metrics's profile picture Deploy HF TF ViTs's profile picture Parti Prompts Diffusers's profile picture Open Generative AI's profile picture UniDiffuser Testing's profile picture Kandinsky Community's profile picture Personal Coding Assistant's profile picture Diffusers Demo at ICCV 2023's profile picture diffusers-adapter's profile picture xin-ic sayak-hf's profile picture PixArt's profile picture huggingPartyParis's profile picture Latent Consistency's profile picture Spatial-T2I's profile picture ZeroGPU Explorers's profile picture SPRIGHT's profile picture PEFT's profile picture NYU VisionX's profile picture Data Is Better Together's profile picture Social Post Explorers's profile picture MaPO's profile picture diffusers-internal-dev's profile picture AuraFlow's profile picture Anonymous T2I Model's profile picture Optimum Internal Testing's profile picture ZP's profile picture Diffusion Guidance's profile picture syn-t2i's profile picture Vchitect-XL's profile picture Data Is Better Together Contributor's profile picture DDUF's profile picture

Posts 13

view post
Post
2332
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
view post
Post
2697
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
View all posts

Collections 2

Optimizing diffusion models
Provides a list of papers focusing on optimizing T2I diffusion models, targeting fewer timesteps, architecture optimization, and more.

Papers 11