Hugging Face's logo

(De)fusing

Activity Feed Request to join this org

AI & ML interests

Fusing diffusion models

Recent Activity

sayakpaulย  authored a paper 28 days ago
A Noise is Worth Diffusion Guidance
abhishekย  authored a paper 2 months ago
AutoTrain: No-code training for state-of-the-art models
sayakpaulย  authored a paper 4 months ago
LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs
View all activity

fusing's activity

sayakpaulย 
posted an update 11 days ago
view post
Post
3746
Commits speak louder than words ๐Ÿคช

* 4 new video models
* Multiple image models, including SANA & Flux Control
* New quantizers -> GGUF & TorchAO
* New training scripts

Enjoy this holiday-special Diffusers release ๐Ÿค—
Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0
anton-lย 
posted an update 16 days ago
view post
Post
2104
Introducing ๐Ÿ“๐…๐ข๐ง๐ž๐Œ๐š๐ญ๐ก: the best public math pre-training dataset with 50B+ tokens!
HuggingFaceTB/finemath

Math remains challenging for LLMs and by training on FineMath we see considerable gains over other math datasets, especially on GSM8K and MATH.

We build the dataset by:
๐Ÿ› ๏ธ carefully extracting math data from Common Crawl;
๐Ÿ”Ž iteratively filtering and recalling high quality math pages using a classifier trained on synthetic annotations to identify math reasoning and deduction.

We conducted a series of ablations comparing the performance of Llama-3.2-3B-Base after continued pre-training on FineMath and observe notable gains compared to the baseline model and other public math datasets.

We hope this helps advance the performance of LLMs on math and reasoning! ๐Ÿš€
Weโ€™re also releasing all the ablation models as well as the evaluation code.

HuggingFaceTB/finemath-6763fb8f71b6439b653482c2
sayakpaulย 
posted an update 17 days ago
view post
Post
1713
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 25 days ago
view post
Post
2069
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
ยท
thomwolfย 
posted an update 26 days ago
view post
Post
4528
We are proud to announce HuggingFaceFW/fineweb-2: A sparkling update to HuggingFaceFW/fineweb with 1000s of ๐Ÿ—ฃ๏ธlanguages.

We applied the same data-driven approach that led to SOTA English performance in๐Ÿท FineWeb to thousands of languages.

๐Ÿฅ‚ FineWeb2 has 8TB of compressed text data and outperforms other multilingual datasets in our experiments.

The dataset is released under the permissive ๐Ÿ“œ ODC-By 1.0 license, and the ๐Ÿ’ป code to reproduce it and our evaluations is public.

We will very soon announce a big community project, and are working on a ๐Ÿ“ blogpost walking you through the entire dataset creation process. Stay tuned!

In the mean time come ask us question on our chat place: HuggingFaceFW/discussion

H/t @guipenedo @hynky @lvwerra as well as @vsabolcec Bettina Messmer @negar-foroutan and @mjaggi
  • 2 replies
ยท
sayakpaulย 
posted an update 26 days ago
view post
Post
2114
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 
authored a paper 28 days ago
thomwolfย 
posted an update 29 days ago
thomwolfย 
posted an update about 1 month ago
abhishekย 
posted an update about 1 month ago
view post
Post
1691
๐ŸŽ‰ SUPER BLACK FRIDAY DEAL ๐ŸŽ‰

Train almost any model on a variety of tasks such as llm finetuning, text classification/regression, summarization, question answering, image classification/regression, object detection, tabular data, etc for FREE using AutoTrain locally. ๐Ÿ”ฅ
https://github.com/huggingface/autotrain-advanced
sayakpaulย 
posted an update about 1 month ago
thomwolfย 
posted an update about 1 month ago
thomwolfย 
posted an update about 2 months ago
sayakpaulย 
posted an update about 2 months ago
view post
Post
2620
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
abhishekย 
posted an update about 2 months ago
view post
Post
5506
INTRODUCING Hugging Face AutoTrain Client ๐Ÿ”ฅ
Fine-tuning models got even easier!!!!
Now you can fine-tune SOTA models on all compatible dataset-model pairs on Hugging Face Hub using Python on Hugging Face Servers. Choose from a number of GPU flavors, millions of models and dataset pairs and 10+ tasks ๐Ÿค—

To try, install autotrain-advanced using pip. You can ignore dependencies and install without --no-deps and then you'd need to install some dependencies by hand.

"pip install autotrain-advanced"

Github repo: https://github.com/huggingface/autotrain-advanced
  • 6 replies
ยท
thomwolfย 
posted an update 2 months ago
view post
Post
4129
Parents in the 1990: Teach the kids to code
Parents now: Teach the kids to fix the code when it starts walking around ๐Ÿค–โœจ
  • 2 replies
ยท
abhishekย 
authored a paper 2 months ago
abhishekย 
posted an update 2 months ago
sayakpaulย 
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
ยท
dn6ย 
posted an update 4 months ago
view post
Post
2658
Sharing for anyone using Diffusers from_single_file loading and affected by the Runway SD 1.5 issue.

If you have runwayml/stable-diffusion-v1-5 saved locally in your HF cache then loading single file checkpoints in the following way should still work. 

from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_single_file("<url or path to single file checkpoint>")


If you do not have the model repo saved in your cache, then automatically inferring the pipeline config will not work since the reference repo runwayml/stable-diffusion-v1-5 doesn't exist anymore.

You can use an alternative SD1.5 repo id to still configure your pipeline.

from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_single_file("<url or path to single file checkpoint>", config="Lykon/DreamShaper")


We're working on resolving the issue ASAP.
  • 2 replies
ยท