Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

Diffusion models
pcuenq 
posted an update 3 days ago
view post
Post
2404
👉 What happened in AI in 2025? 👈

We prepared the 2025 version of the HF AI Timeline Grid, highlighting open vs API-based model releases, and allowing you to browse and filter by access, modality, and release type!

Play with it here:
2025-ai-timeline/2025-ai-timeline

Here's my personal quarterly TL;DR:

1️⃣ Q1 — Learning to Reason
Deepseek not only releases a top-notch reasoning model, but shows how to train them and compete with closed frontier models. OpenAI debuts Deep Research.

Significant milestones: DeepSeek R1 & R1-Zero, Qwen 2.5 VL, OpenAI Deep Research, Gemini 2.5 Pro (experimental)

2️⃣ Q2 — Multimodality and Coding
More LLMs embrace multimodality by default, and there's a surge in coding agents. Strong vision, audio, and generative models emerge.

Significant milestones: Llama 4, Qwen 3, Imagen 4, OpenAI Codex, Google Jules, Claude 4

3️⃣ Q3 — "Gold" rush, OpenAI opens up, the community goes bananas
Flagship models get gold in Math olympiads and hard benchmarks. OpenAI releases strong open source models and Google releases the much anticipated nano-banana for image generation and editing. Agentic workflows become commonplace.

Significant milestones: Gemini and OpenAI IMO Gold, gpt-oss, Gemini 2.5 Flash Image, Grok 4, Claude Sonnet 4.5

4️⃣ Q4 — Mistral returns, leaderboard hill-climbing
Mistral is back with updated model families. All labs release impressive models to wrap up the year!

Significant milestones: Claude Opus 4.5, DeepSeek Math V2, FLUX 2, GPT 5.1, Kimi K2 Thinking, Nano Banana Pro, GLM 4.7, Gemini 3, Mistral 3, MiniMax M2.1 🤯

Credits
🙏 NHLOCAL for the source data https://github.com/NHLOCAL/AiTimeline

🫡 @reach-vb for the original idea, design and recipe

🙌 @ariG23498 and yours truly for compiling and verifying the 2025 edition

🥳 Here's to 2026, wishing it becomes the best year ever for open releases and on-device-first use-cases! 🥂
  • 1 reply
·
sayakpaul 
authored a paper 3 months ago
sayakpaul 
posted an update 6 months ago
view post
Post
2076
Fast LoRA inference for Flux with Diffusers and PEFT 🚨

There are great materials that demonstrate how to optimize inference for popular image generation models, such as Flux. However, very few cover how to serve LoRAs fast, despite LoRAs being an inseparable part of their adoption.

In our latest post, @BenjaminB and I show different techniques to optimize LoRA inference for the Flux family of models for image generation. Our recipe includes the use of:

1. torch.compile
2. Flash Attention 3 (when compatible)
3. Dynamic FP8 weight quantization (when compatible)
4. Hotswapping for avoiding recompilation during swapping new LoRAs 🤯

We have tested our recipe with Flux.1-Dev on both H100 and RTX 4090. We achieve at least a *2x speedup* in either of the GPUs. We believe our recipe is grounded in the reality of how LoRA-based use cases are generally served. So, we hope this will be beneficial to the community 🤗

Even though our recipe was tested primarily with NVIDIA GPUs, it should also work with AMD GPUs.

Learn the details and the full code here:
https://huggingface.co/blog/lora-fast
  • 3 replies
·
sayakpaul 
posted an update 8 months ago
view post
Post
2925
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
  • 2 replies
·
sayakpaul 
posted an update 8 months ago
view post
Post
1864
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 months ago
sayakpaul 
authored a paper 9 months ago
pcuenq 
authored a paper 9 months ago
sayakpaul 
authored a paper 10 months ago
sayakpaul 
posted an update 11 months ago
view post
Post
3958
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 11 months ago
view post
Post
2160
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 12 months ago
view post
Post
2090
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 about 1 year ago
sayakpaul 
posted an update about 1 year ago
view post
Post
2306
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 about 1 year ago
view post
Post
2223
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
  • 8 replies
·
sayakpaul 
posted an update about 1 year ago
view post
Post
2243
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 about 1 year ago
sayakpaul 
posted an update about 1 year ago
sayakpaul 
posted an update about 1 year ago
view post
Post
2760
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 over 1 year ago
view post
Post
2831
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
·