Hugging Face's logo

diffusers-adapter

community
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

sayakpaul  authored a paper 8 days ago
Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis
sayakpaul  authored a paper about 1 month ago
From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning
sayakpaul  authored a paper 2 months ago
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
View all activity

diffusers-adapter's activity

sayakpaul 
posted an update 2 days ago
view post
Post
2086
Diffusers supports a good variety of quantization backends. It can be challenging to navigate through them, given the complex nature of diffusion pipelines in general.

So, @derekl35 set out to write a comprehensive guide that puts users in the front seat. Explore the different backends we support, learn the trade-offs they offer, and finally, check out the cool space we built that lets you compare quantization results.

Give it a go here:
https://lnkd.in/gf8Pi4-2
sayakpaul 
posted an update 4 days ago
view post
Post
1567
Despite the emergence of combining LLM and DiT architectures for T2I synthesis, its design remains severely understudied.

This was done long ago and got into CVPR25 -- super excited to finally share it now, along with the data and code ♥️

We explore several architectural choices that affect this design. We provide an open & reproducible training recipe that works at scale.

Works like Playground v3 have already explored a deep fusion between an LLM and a DiT, sharing their representations through layerwise attention. They exhibit excellent performance on T2I.

Despite its compelling results and other performance virtues, it remains unexplored, which is what we want to improve in our work. Specifically, we take a pre-trained LLM (Gemma-2B) and trainable DiT, and set out to explore what makes a "good deep fusion" between the two for T2I.

We explore several key questions in the work, such as:

Q1: How should we do attention? We considered several alternatives. PixArt-Alpha like attention (cross-attention) is very promising.
Q2: Should we incorporate additional text modulation?
Q3: Can we eliminate timestep conditioning?
Q4: How do we do positional encodings?
Q5: Do instruction-tuned LLMs help deep fusion?
Q6: Would using a decoder LLM from a multimodal model be helpful?
Q7: Does using a better variant of Gemma help?

Based on the above findings, we arrive at FuseDiT with the following components on top of the base architecture from the findings of our experiments.

* No AdaLN-Zero modules
* 1D + 2D-RoPE
* Gemma 2 2B, adjusting DiT configurations accordingly

We trained FuseDiT on a mixture from CC12M, JourneyDB, & SA (~26M image-text pairs) for 800 steps. While not the best model, it's encouraging to develop something in a guided manner using open datasets.

To know more (code, models, all are available), please check out the paper:
https://lnkd.in/gg6qyqZX.
sayakpaul 
authored a paper 8 days ago
sayakpaul 
authored a paper about 1 month ago
sayakpaul 
authored a paper 2 months ago
sayakpaul 
posted an update 3 months ago
view post
Post
3846
Inference-time scaling meets Flux.1-Dev (and others) 🔥

Presenting a simple re-implementation of "Inference-time scaling diffusion models beyond denoising steps" by Ma et al.

I did the simplest random search strategy, but results can potentially be improved with better-guided search methods.

Supports Gemini 2 Flash & Qwen2.5 as verifiers for "LLMGrading" 🤗

The steps are simple:

For each round:

1> Starting by sampling 2 starting noises with different seeds.
2> Score the generations w.r.t a metric.
3> Obtain the best generation from the current round.

If you have more compute budget, go to the next search round. Scale the noise pool (2 ** search_round) and repeat 1 - 3.

This constitutes the random search method as done in the paper by Google DeepMind.

Code, more results, and a bunch of other stuff are in the repository. Check it out here: https://github.com/sayakpaul/tt-scale-flux/ 🤗
sayakpaul 
posted an update 4 months ago
view post
Post
2100
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: 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
  • 1 reply
·
sayakpaul 
posted an update 4 months ago
view post
Post
2042
We have authored a post to go over the state of video generation in the Diffusers ecosystem 🧨

We cover the models supported, the knobs of optims our users can fire, fine-tuning, and more 🔥

5-6GBs for HunyuanVideo, sky is the limit 🌌 🤗
https://huggingface.co/blog/video_gen
sayakpaul 
posted an update 5 months ago
sayakpaul 
posted an update 5 months ago
view post
Post
2261
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 6 months ago
view post
Post
2187
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 6 months ago
view post
Post
2211
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 6 months ago
sayakpaul 
posted an update 6 months ago
sayakpaul 
posted an update 6 months ago
view post
Post
2726
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
·
sayakpaul 
posted an update 8 months ago
view post
Post
2809
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
·
sayakpaul 
authored a paper 9 months ago
sayakpaul 
posted an update 9 months ago
sayakpaul 
posted an update 10 months ago
view post
Post
4535
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 10 months ago
view post
Post
3839
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
·