Sayak Paul's picture

Sayak Paul

sayakpaul

·

https://sayak.dev

AI & ML interests

Diffusion models, representation learning

Articles

🧨 Diffusers welcomes Stable Diffusion 3.5 Large

Memory-efficient Diffusion Transformers with Quanto and Diffusers

🧨 Diffusers welcomes Stable Diffusion 3

🤗 PEFT welcomes new merging methods

Welcome aMUSEd: Efficient Text-to-Image Generation

SDXL in 4 steps with Latent Consistency LoRAs

Personal Copilot: Train Your Own Coding Assistant

Exploring simple optimizations for SDXL

Finetune Stable Diffusion Models with DDPO via TRL

Introducing Würstchen: Fast Diffusion for Image Generation

Efficient Controllable Generation for SDXL with T2I-Adapters

Happy 1st anniversary 🤗 Diffusers!

Optimizing Stable Diffusion for Intel CPUs with NNCF and 🤗 Optimum

Instruction-tuning Stable Diffusion with InstructPix2Pix

Training a language model with 🤗 Transformers using TensorFlow and TPUs

ControlNet in Diffusers 🧨

🤗 PEFT: Parameter-Efficient Fine-Tuning of Billion-Scale Models on Low-Resource Hardware

A Dive into Pretraining Strategies for Vision-Language Models

The State of Computer Vision at Hugging Face 🤗

Using LoRA for Efficient Stable Diffusion Fine-Tuning

Image Similarity with Hugging Face Datasets and Transformers

Deploying 🤗 ViT on Vertex AI

Deploying 🤗 ViT on Kubernetes with TF Serving

Deploying TensorFlow Vision Models in Hugging Face with TF Serving

Organizations

sayakpaul's activity

New activity in sayakpaul/flux.1-schell-int8wo-improved 10 days ago

VRAM usage jumps above 24GB at the end of inference

#2 opened 10 days ago by

New activity in Wild-Heart/Disney-VideoGeneration-Dataset 11 days ago

Have both Videos and Prompts in the Viewer

#4 opened 11 days ago by

New activity in SPRIGHT-T2I/spright about 1 month ago

File names: no leading zeroes

#5 opened about 1 month ago by

Update README.md

#6 opened about 1 month ago by

New activity in sayakpaul/FLUX.1-merged about 1 month ago

add base_model_relation too

#12 opened about 1 month ago by

Add multiple base_model

#11 opened about 1 month ago by

New activity in sayakpaul/flux-lora-resizing about 1 month ago

How to Use Safetensor Directly without loading whole model

#1 opened about 1 month ago by

New activity in huggingface/documentation-images about 2 months ago

Upload astronaut.jpg

#367 opened about 2 months ago by

New activity in sayakpaul/flux.1-schell-int8wo-improved 2 months ago

what's the difference between the imporved version with the last verison?

#1 opened 2 months ago by

New activity in qwertyforce/watermark_detection 2 months ago

Usage

#1 opened 2 months ago by

New activity in hf-internal-testing/flux.1-dev-nf4-pkg 2 months ago

if not use enable_model_cpu_offload(); How much does it take to run all on the gpu?

#2 opened 2 months ago by

A request or wish for the final specification to be like this

#1 opened 2 months ago by

New activity in sayakpaul/flux.1-dev-nf4-with-bnb-integration 2 months ago

ValueError

#1 opened 2 months ago by

ImportError: Using `bitsandbytes` 4-bit quantization requires the latest version of bitsandbytes: `pip install -U bitsandbytes`

#2 opened 2 months ago by

New activity in sayakpaul/poses-controlnet-dataset 2 months ago

Update task tag

#1 opened 2 months ago by

New activity in sayakpaul/flux.1-dev-nf4 3 months ago

Apology and Notification

#2 opened 3 months ago by

New activity in dataautogpt3/FluxteusV1 3 months ago

On the Diffusers code example

#1 opened 3 months ago by

New activity in sayakpaul/flux.1-dev-nf4 3 months ago

Not load with nf4

#1 opened 3 months ago by

commented a paper 3 months ago

CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

Paper • 2408.06072 • Published Aug 12 • 35 •

New activity in sayakpaul/FLUX.1-merged 3 months ago

Why does it work?

#10 opened 3 months ago by