Sayak Paul's picture

Sayak Paul

sayakpaul

·

https://sayak.dev

AI & ML interests

Diffusion models, representation learning

Recent Activity

upvoted an article 5 days ago

The AI tools for Art Newsletter - Issue 1

updated a dataset 7 days ago

sayakpaul/arxiv-new-datasets

posted an update 7 days ago

We have been cooking a couple of fine-tuning runs on CogVideoX with finetrainers, smol datasets, and LoRA to generate cool video effects like crushing, dissolving, etc. We are also releasing a LoRA extraction utility from a fully fine-tuned checkpoint. I know that kind of stuff has existed since eternity, but the quality on video models was nothing short of spectacular. Below are some links: * Models and datasets: https://huggingface.co/finetrainers * finetrainers: https://github.com/a-r-r-o-w/finetrainers * LoRA extraction: https://github.com/huggingface/diffusers/blob/main/scripts/extract_lora_from_model.py

View all activity

Organizations

sayakpaul's activity

New activity in ariG23498/flux-edit 7 days ago

Update requirements.txt

#5 opened 7 days ago by

Update app.py to acknowledge ByteDance

#2 opened 7 days ago by

New activity in Spawning/pd12m-full 10 days ago

Why do the tar filenames begin at 155?

#2 opened 13 days ago by

New activity in huggingface/documentation-images 14 days ago

Add Flux IP-Adapter example

#424 opened 14 days ago by

New activity in finetrainers/pika-dissolve-v0 23 days ago

Fix Gallery component

#1 opened 23 days ago by

New activity in huggingface/documentation-images 23 days ago

Add ParaAttention Images and Videos

#416 opened 23 days ago by

New activity in sayakpaul/q8-ltx-video 24 days ago

L4 fix

#1 opened 24 days ago by

New activity in sayakpaul/flux.1-schell-int8wo-improved 24 days ago

VRAM usage jumps above 24GB at the end of inference

#2 opened 3 months ago by

New activity in sayakpaul/vae-sd-imagenet-256-latents about 1 month ago

purpose

#1 opened about 1 month ago by

New activity in hunyuanvideo-community/HunyuanVideo about 1 month ago

Black output

#1 opened about 1 month ago by

New activity in black-forest-labs/FLUX.1-Fill-dev about 2 months ago

Can't use latest diffusers ?

#24 opened about 2 months ago by

New activity in city96/LTX-Video-gguf about 2 months ago

Update README.md to include a note about loading in `diffusers`

#4 opened about 2 months ago by

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

consisid-images

#406 opened about 2 months ago by

New activity in Lightricks/LTX-Video about 2 months ago

Update README.md to include diffusers usage

#42 opened about 2 months ago by

New activity in black-forest-labs/FLUX.1-Canny-dev-lora about 2 months ago

Update README.md to include diffusers usage

#2 opened about 2 months ago by

New activity in black-forest-labs/FLUX.1-Depth-dev-lora about 2 months ago

Update README.md to include the `diffusers` usage

#2 opened about 2 months ago by

New activity in diffusers/FLUX.1-Fill-dev-nf4 2 months ago

How to load in ComfyUi? tried using the Load NF4 Flux UNET.

#2 opened 2 months ago by

New activity in DDUF/dduf-check 2 months ago

Add txt extension to DDUF

#1 opened 2 months ago by

New activity in Wild-Heart/Disney-VideoGeneration-Dataset 2 months ago

Have both Videos and Prompts in the Viewer

#4 opened 3 months ago by

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

run

#5 opened 2 months ago by