NYU VisionX

university
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

nyu-visionx's activity

sayakpaulย 
posted an update 5 days ago
view post
Post
1489
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
ยท
sayakpaulย 
posted an update 13 days ago
view post
Post
2025
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
ยท
sayakpaulย 
posted an update 14 days ago
view post
Post
2088
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 ๐Ÿค—

It's still WIP, so go easy:
https://github.com/huggingface/diffusers/pull/10130
sayakpaulย 
posted an update 24 days ago
sayakpaulย 
posted an update about 1 month ago
view post
Post
2594
It's been a while we shipped native quantization support in diffusers ๐Ÿงจ

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
ยท
sayakpaulย 
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
ยท
sayakpaulย 
posted an update 4 months ago