Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Quick test with SDXL Turbo, another amazing, super-fast diffusion model. It works right out of the box with diffusers unofficial demo txt2img and img2img:

Radamés Ajna

6,832 subscribers

219,846 views • 2 years ago •via X (Twitter)

Arts Education Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

SkalskiP2 years ago

@diffuserslib This is insane…

1LittleCoder💻2 years ago

@diffuserslib Your demos are addicitive and inspiring!

Ankush Singal2 years ago

@diffuserslib Is it faster compared to using with LCM ? Cheaper?

blender_ovo2 years ago

@diffuserslib super lcm！

🟢 ٴ` b0gie.eth🟣2 years ago

@diffuserslib @Crypto_koH

かつお節2 years ago

@osanseviero @diffuserslib cat power

JunMa2 years ago

@diffuserslib Thanks for sharing. This is super cool. Is there any way to fine-tune the model for img2img task?

bondarchukb2 years ago

@diffuserslib hmm, idk why but its working quite slow on my side, maybe because a lot of users are testing it?

Sylwester Mielniczuk 🔮💎2 years ago

@diffuserslib Trying to get the models, it's over 30G....

starwave2 years ago

@diffuserslib It continues to blow my mind how things got so fast that you can just prompt and then surf through seeds and steps now at lightning speed to help find the image you're looking for rather than having to modify the prompt all the time, whole new way to explore!

Related Videos

Thanks to the Latent Consistency Model (LCM), we're nearing real-time image diffusion. I've made a simple MJPEG server for generation stream using diffusers img2img pipeline. It's really fun to play with it. Can't wait for the ControlNet version. try it:

Thanks to the Latent Consistency Model (LCM), we're nearing real-time image diffusion. I've made a simple MJPEG server for generation stream using diffusers img2img pipeline. It's really fun to play with it. Can't wait for the ControlNet version. try it:

Radamés Ajna

231,829 views • 2 years ago

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:

Stability AI

976,258 views • 2 years ago

Inpainting with Qwen Edit is like working with a magic brush amazing how well it works out of the box

Inpainting with Qwen Edit is like working with a magic brush amazing how well it works out of the box

Linoy Tsaban

14,561 views • 9 months ago

Do diffusion models want Perlin-like noise? SDXL-turbo spends the first blocks simply creating Perlin-like noise of different frequencies, amplitudes and orientations. The model ignores the prompt conditioning during these layers.

Do diffusion models want Perlin-like noise? SDXL-turbo spends the first blocks simply creating Perlin-like noise of different frequencies, amplitudes and orientations. The model ignores the prompt conditioning during these layers.

Rudy Gilman

59,764 views • 1 year ago

This is getting interesting. In this iteration, the magnifying glass is tracked in real-time, feeding only what is seen through it to the diffusion process, revealing the invisible within a piece of clay. Real-time diffusion with Stream Diffusion + SDXL Turbo. #StableDiffusion #SDXLTurbo #StreamDiffusion #StabilityAI #Realtime

This is getting interesting. In this iteration, the magnifying glass is tracked in real-time, feeding only what is seen through it to the diffusion process, revealing the invisible within a piece of clay. Real-time diffusion with Stream Diffusion + SDXL Turbo. #StableDiffusion #SDXLTurbo #StreamDiffusion #StabilityAI #Realtime

Hugues Bruyère

26,432 views • 2 years ago

🚀Meet Gemini Diffusion, our first diffusion-based and super fast language model, just announced at Google I/O!🚀 Very excited to be able to share what I've been working on for the past little while with our amazing small team Google DeepMind.

🚀Meet Gemini Diffusion, our first diffusion-based and super fast language model, just announced at Google I/O!🚀 Very excited to be able to share what I've been working on for the past little while with our amazing small team Google DeepMind.

Ivana Balazevic

43,469 views • 1 year ago

PAIR-Diffusion: Object-Level Image Editing with Structure-and-Appearance Paired Diffusion Models Gradio demo is out on Hugging Face Spaces demo:

PAIR-Diffusion: Object-Level Image Editing with Structure-and-Appearance Paired Diffusion Models Gradio demo is out on Hugging Face Spaces demo:

AK

87,679 views • 3 years ago

Tonight I grabbed some other ingredients: milk from the kitchen and black ink from my son. Watching the images emerge is like clearing my mind. Some parts of this video have been sped up 4x, while others are in real-time. Real-time diffusion with Stream Diffusion + SDXL Turbo. #StableDiffusion #SDXLTurbo #StreamDiffusion #StabilityAI #Realtime

Tonight I grabbed some other ingredients: milk from the kitchen and black ink from my son. Watching the images emerge is like clearing my mind. Some parts of this video have been sped up 4x, while others are in real-time. Real-time diffusion with Stream Diffusion + SDXL Turbo. #StableDiffusion #SDXLTurbo #StreamDiffusion #StabilityAI #Realtime

Hugues Bruyère

45,718 views • 2 years ago

try out the Gradio Demo for AudioLDM: Text-to-Audio Generation with Latent Diffusion Models on Hugging Face demo:

try out the Gradio Demo for AudioLDM: Text-to-Audio Generation with Latent Diffusion Models on Hugging Face demo:

AK

82,137 views • 3 years ago

🔅test🔅 LUA, with demo, still works on 12.50! #PS4

🔅test🔅 LUA, with demo, still works on 12.50! #PS4

🇲‌🇴‌🇺‌🇺‌🇺‌㋡ ▢ △ 🆇

32,069 views • 1 year ago

MolmoAct2 kinda just works out of the box in an unseen environment and with unseen objects. I find it really crazy that I can just download a model from the internet and plug it into my robot and it can do some tasks at a limited capacity right away. this video is at 2x speed

MolmoAct2 kinda just works out of the box in an unseen environment and with unseen objects. I find it really crazy that I can just download a model from the internet and plug it into my robot and it can do some tasks at a limited capacity right away. this video is at 2x speed

atharva ☆

31,832 views • 1 month ago

I spent a day at the Tutor office chatting with Josh Gruenstein on what it takes to bring rapidly deployed robotics to industrial scale. Check it out here (and catch my test drive of an in-the-works new model):

I spent a day at the Tutor office chatting with Josh Gruenstein on what it takes to bring rapidly deployed robotics to industrial scale. Check it out here (and catch my test drive of an in-the-works new model):

Rebecca Kaden

27,827 views • 6 months ago

Curious how it works? Check out this demo where the model solves a tricky probability problem.

Curious how it works? Check out this demo where the model solves a tricky probability problem.

Noam Shazeer

153,353 views • 1 year ago

shadcn/create works out of the box with Laravel Run laravel new, build your preset then apply it using the cli.

shadcn/create works out of the box with Laravel Run laravel new, build your preset then apply it using the cli.

shadcn

72,847 views • 3 months ago

（*゜ー゜*） Sound On Please! ComfyUI workflow for turning SDXL Turbo outputs into a video! Pass it folder of SDXL Turbo frames or any folder of frames. This piece is called: 'God of Time' Audio by me as well. Workflow here:

（゜ー゜） Sound On Please! ComfyUI workflow for turning SDXL Turbo outputs into a video! Pass it folder of SDXL Turbo frames or any folder of frames. This piece is called: 'God of Time' Audio by me as well. Workflow here:

無限 💀 acc/acc

15,179 views • 2 years ago

Here's a quick demo on how it works

Here's a quick demo on how it works

Moment Pro Camera

33,791 views • 5 months ago

Quick test of CC Vector Blur for a magma-style effect. Works nicely with CC Particle World

Quick test of CC Vector Blur for a magma-style effect. Works nicely with CC Particle World

Denys Bondartsov 🇺🇦

26,882 views • 1 year ago

Here’s a small demo of an agent I built called Turbo. Turbo perceives what’s on screen and operates MacOS with the mouse and keyboard — like a human. It’s smart and it’s fast (and getting faster). Imagine Clawdbot/Openclaw with Turbo! I’ll likely open-source this, but before I do, I’m looking for someone to join me. DMs are open.

Here’s a small demo of an agent I built called Turbo. Turbo perceives what’s on screen and operates MacOS with the mouse and keyboard — like a human. It’s smart and it’s fast (and getting faster). Imagine Clawdbot/Openclaw with Turbo! I’ll likely open-source this, but before I do, I’m looking for someone to join me. DMs are open.

Allan

29,783 views • 4 months ago

Large Language Diffusion with Masking (LLaDA) are here - and their generation looks so fucking dope! 🤯 True to Yann LeCun's vision, Ditch the auto-regressive bits and approximate the language distribution via Maximum Likelihood Estimation! So cool to watch the model denoise text from tokens in real time! - The team released their model checkpoints and there's a demo for you to play with it too! Try it out!🤗

Large Language Diffusion with Masking (LLaDA) are here - and their generation looks so fucking dope! 🤯 True to Yann LeCun's vision, Ditch the auto-regressive bits and approximate the language distribution via Maximum Likelihood Estimation! So cool to watch the model denoise text from tokens in real time! - The team released their model checkpoints and there's a demo for you to play with it too! Try it out!🤗

Vaibhav (VB) Srivastav

21,394 views • 1 year ago