Hugging Face's logo

PixArt

community
https://pixart-alpha.github.io
PixArt-alpha
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

sayakpaul  authored a paper 27 days ago
A Noise is Worth Diffusion Guidance
Lawrence-cj  authored a paper about 1 month ago
MetaBEV: Solving Sensor Failures for BEV Detection and Map Segmentation
Lawrence-cj  authored a paper about 1 month ago
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
View all activity

PixArt-alpha's activity

sayakpaul 
posted an update 9 days ago
sayakpaul 
posted an update 15 days ago
view post
Post
1685
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
·
sayakpaul 
posted an update 23 days ago
view post
Post
2065
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
  • 7 replies
·
sayakpaul 
posted an update 24 days ago
view post
Post
2113
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 🤗

It's still WIP, so go easy:
https://github.com/huggingface/diffusers/pull/10130
sayakpaul 
authored a paper 27 days ago
sayakpaul 
posted an update about 1 month ago
Lawrence-cj 
authored 3 papers about 1 month ago
sayakpaul 
posted an update about 2 months ago
view post
Post
2616
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
·
Lawrence-cj 
updated a Space 3 months ago
sayakpaul 
posted an update 3 months ago
view post
Post
2756
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
·
Lawrence-cj 
updated a Space 4 months ago
sayakpaul 
authored a paper 4 months ago
sayakpaul 
posted an update 5 months ago
sayakpaul 
posted an update 5 months ago
view post
Post
4481
Flux.1-Dev like images but in fewer steps.

Merging code (very simple), inference code, merged params: sayakpaul/FLUX.1-merged

Enjoy the Monday 🤗
·
sayakpaul 
posted an update 5 months ago
view post
Post
3796
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
·
Lawrence-cj 
updated 2 datasets 5 months ago
Lawrence-cj 
updated a dataset 6 months ago