Yes you're speaking with the 🤗 @huggingface 🧨 diffusers library personally
Joined November 2022
- Tweets128
- Following22
- Followers2.9K
- Likes103
diffusers retweeted
The demo is live! xitter.cf/multimodalart/status/1…
Adding true CFG to FLUX [dev] gives it style superpowers! 🦸
You can now try a demo of flux with CFG on @huggingface!
▶️ huggingface.co/spaces/multim…
diffusers retweeted
Video-to-video is now available in the official CogVideoX-5B Space 🔥
Try it out 🎥 ➡️🎥
huggingface.co/spaces/THUDM/…
diffusers retweeted
We now support loading and inferencing with two non-diffusers Flux LoRAs
1> X-Labs
2> Kohya (@kohya_tech)
Thanks to @multimodalart for jamming on this with me!
github.com/huggingface/diffu…
diffusers retweeted
CogVideoX just released the weights for its 5B model! 🎥 ✨
It's the best open weights text-to-video model - competitive with Runway / Luma / Pika. With 🧨@diffuserslib, it fits on < 10GB VRAM 🤏
(ah, and they changed the smaller 2B model license to Apache 2.0 🔥)
diffusers retweeted
Now, PAG is officially supported by Diffusers in the stable version! Try it out🥰
Use cases: huggingface.co/docs/diffuser…
Supported pipelines: huggingface.co/docs/diffuser…
We would like to extend our gratitude to the amazing team at @huggingface for their incredible work. Special thanks to @RisingSayak for taking charge of PixArt-Sigma, @aryanvs_ for taking HunyuanDiT and refactoring the code brilliantly, @OzzyGT for handling Kolors and conducting numerous experiments, @multimodalart for being an early adopter and advocate, and @YiYiMarz for designing the overall framework for PAG pipelines.
we just dropped an insane new release 🐣
- support to new pipelines: audio 🔊, video 🎬 and image 🖼️ models (FLUX, Stable Audio, CogVideoX, Kolors, AuraFlow and moar!)
- native PAG support for image quality boost 💨
- AnimatedDiff 🤝 SparseCtrl
github.com/huggingface/diffu…
diffusers retweeted
The first open Stable Diffusion 3-like architecture model is JUST out 💣 - but it is not SD3! 🤔
It is HunyuanDiT by Tencent, a 1.5B parameter DiT (diffusion transformer) text-to-image model 🖼️✨
In the paper they claim to be SOTA open source! I'm working on a @huggingface demo as you read this so we can all vibe check
Model: huggingface.co/Tencent-Hunyu…
GitHub: github.com/Tencent/HunyuanDi…
Paper: tencent.github.io/HunyuanDiT…
diffusers retweeted
Demo for the first open SD3-like architecture model, HunyuanDiT @huggingface Spaces demo is out! 🎨
First impressions:
- Image quality seems very good!
- Chunky and the research code isn't super optimized for inference speed (👋 @diffuserslib 👀)
▶️ huggingface.co/spaces/multim…
The first open Stable Diffusion 3-like architecture model is JUST out 💣 - but it is not SD3! 🤔
It is HunyuanDiT by Tencent, a 1.5B parameter DiT (diffusion transformer) text-to-image model 🖼️✨
In the paper they claim to be SOTA open source! I'm working on a @huggingface demo as you read this so we can all vibe check
Model: huggingface.co/Tencent-Hunyu…
GitHub: github.com/Tencent/HunyuanDi…
Paper: tencent.github.io/HunyuanDiT…
diffusers retweeted
🧨 diffusers reached 20k stars on GitHub 💫
But like many others, I am not a firm believer in this metric. So, let's also consider the number of repos that rely on it and the SUM of their stars. This gives a better view point about the library 🤗
Thanks to all our contributors for making it awesome!
diffusers retweeted
Introducing the smallest Distil-Whisper model yet!
distil-small.en is over 10x smaller, 5x faster and within 3% WER of large-v2 🎯
At just 166M parameters, it's is perfect for low-memory environments, such as on-device or mobile 📞
Get started here: huggingface.co/distil-whispe…
diffusers retweeted
MagicAnimate: 💃 Temporally Consistent Human Image Animation using Diffusion Model 🕺 Colab 🥳
Thanks to Zhongcong Xu ❤ Jianfeng Zhang ❤ Jun Hao Liew ❤ Hanshu Yan ❤ Jia-Wei Liu ❤ Chenxu Zhang ❤ Jiashi Feng ❤ @MikeShou1 ❤
🌐page: showlab.github.io/magicanima…
📄paper: arxiv.org/abs/2311.16498
🧬code: github.com/magic-research/ma…
🦒colab by modelslab.com: please try it 🐣 github.com/camenduru/MagicAn…
diffusers retweeted
Playground V2 has been included in the genAI Blender add-on, Pallaidium. github.com/tin2tin/Pallaidiu…
#b3d #playgroundv2 #genAI
diffusers retweeted
Loading LoRAs for inference on @huggingface is now 300% faster: LoRAs are hot-swapped and the base model is kept warm 🥵
All users can benefit from this via the free Inference API/Widget 🌍
Check out the deep dive by Raphael Glon 👇
huggingface.co/blog/lora-ada…
diffusers retweeted
🎅 Santa has arrived early with this latest wandb python release! Included in wandb 0.16.1 are:
⭐️ a clean new `log_model` api for logging model checkpoints to @wandb:
wandb.log_model(
name="", path=""
)
⭐️ @OpenAI 1-line fine-tuning integration:
`wandblogger.sync()`
⭐️ @diffuserslib pipeline autologging, 1 line autologging of calls to your diffusers pipelines:
`from wandb.integration.diffusers import autolog`
Deep dives on each coming soon :D
diffusers retweeted
Playground v2: A new commercially open model 🎊 Colab 🥳
Thanks to @playground_ai Team ❤ @Suhail ❤
🌐page: blog.playgroundai.com/playgr…
📦model: huggingface.co/playgroundai/…
🦒colab by modelslab.com: please try it 🐣 github.com/camenduru/playgro…
diffusers retweeted
In a couple of weeks, we went from LCM LoRa getting about ~5fps to now ~17fps with the latest SD-Turbo distilled model. Thanks @StabilityAI the quality with SD-Turbo is incredible! Video is at normal speed. see Musk and Gates with curly hair 😅
demo: huggingface.co/spaces/radame…
diffusers retweeted
Ramping up the Stable Video Diffusion with 🧨 diffusers!
folks from @diffuserslib just merged compatibility with SVD - I updated my demo to use it - uses less VRAM 🤏, runs faster 🏃🏻⚡️ with torch.compile(), which means smaller queues for the demo
▶️ huggingface.co/spaces/multim…
diffusers retweeted
Hugging Face released a Colab Notebook for generation from SDXL Turbo using the diffusers library: colab.research.google.com/dr…
diffusers retweeted
In other news, Japanese Stable Diffusion XL (JSDXL) was released today by @StabilityAI_JP, おめでとう、友よ 🤗
このモデルは @huggingface でデモできます。
Play with it on Spaces ▶️ huggingface.co/spaces/stabil…
diffusers retweeted
Stable Diffusion 360 Panorama Colab 🥳 Thanks to Mengyang Feng ❤
🌐page: modelscope.cn/models/damo/cv…
🧬code: github.com/ArcherFMY/SD-T2I-…
📦model: huggingface.co/archerfmy0831…
🦒colab: please try it 🐣 github.com/camenduru/SD-T2I-…
diffusers retweeted
Little @Gradio ❤ code 🌿 and little @diffuserslib ❤ code 🍅 real-time drawing app is done 🥗
Thanks to @SimianLuo (LCM) ❤ @Gradio Team ❤ @diffuserslib Team ❤
🦒colab: please try it 🐣 github.com/camenduru/latent-…