正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Back in the lab this week updating Kinetic Diffusion, our AI powered dance performance, with new Stable Diffusion models. Speed and pixels have increased tremendously unlocking new opportunities. Here’s an experiment in “popping” new prompts in with connection to the movement ⬇️

Brandon Powers

1,980 subscribers

128,731 次观看 • 2 年前 •via X (Twitter)

艺术教育科学技术

Anya Rossi• Live Now

Private livecam show

10 条评论

Brandon Powers 的头像

Brandon Powers2 年前

Another new experiment…we can play with frame rate and how we capture my movement to create some flipbook-esque echos

Brandon Powers 的头像

Brandon Powers2 年前

Thanks to everyone for the amazing support on this post! I strongly believe AI is a TOOL for creativity, not a replacement, and this project is all about how artists are fundamental to exploring the boundaries of technology. Here’s an explainer on how we’ve build the dance:

Brian Jordan 的头像

Brian Jordan2 年前

@StableDiffusion So sick! Curious are y'all using LCM / SD Turbo / Stream Diffusion for this? (Been playing around w various realtime rendering methods a bit this last month) cc @fal_ai_data

Brandon Powers 的头像

Brandon Powers2 年前

@StableDiffusion @fal_ai_data Yeah we’re using Turbo combined with a custom platform we built for this. We had near real time back in June and now the new model really gets it close and cuts compute MAJORLY. It took 20 computers, now it takes 3.

Emre YILMAZ 的头像

Emre YILMAZ2 年前

@EMostaque @StableDiffusion This is fantastic. Textbook definition for creativity. We have been playing with real-time LCMs for a while yet this is the most creative way to harness their power among dozens of cases I've observed. Drawing through dancing / Filming-making through dancing. I salute you.

Brandon Powers 的头像

Brandon Powers2 年前

@EMostaque @StableDiffusion Thank you! I’ve been working with dance and AI for over 5 years now, so access to these new models has allowed us to really explore clear and powerful techniques. Art helps the world understand this tech better than anything. Keep on building! We’re in this together 💪

Sevy Silva ™️ 的头像

Sevy Silva ™️2 年前

@StableDiffusion Soooooo impressive!!! @Twelvisten this is kinda what we were yesterday talking about!!! Is CRAZY ❤️‍🔥

Jimmy6DOF 的头像

Jimmy6DOF2 年前

@StableDiffusion channeling a bit of this @graycrawford and knocking it out of the park ...... soooo much potential here !!! Bravo ! Encore !

Amir 的头像

Amir2 年前

@StableDiffusion Amazing!

Captain HaHaa 的头像

Captain HaHaa2 年前

@StableDiffusion wooooahh! that's cool! Well done mate

相关视频

In our new short course you’ll learn exactly how algorithms like DALL·E and Stable Diffusion work. Dive into the fascinating world of diffusion models and build your own model from scratch with Sharon Zhou ✈️ ICML in "How Diffusion Models Work." Sign up:

In our new short course you’ll learn exactly how algorithms like DALL·E and Stable Diffusion work. Dive into the fascinating world of diffusion models and build your own model from scratch with Sharon Zhou ✈️ ICML in "How Diffusion Models Work." Sign up:

DeepLearning.AI

56,075 次观看 • 3 年前

Today, we’re thrilled to announce the open weights for Stable Diffusion 3 Medium, the latest and most advanced text-to-image AI model in our Stable Diffusion 3 series! This new release represents a major milestone in the evolution of generative AI and continues our commitment to democratising this powerful technology. 🎉 Learn more and get started here:

Today, we’re thrilled to announce the open weights for Stable Diffusion 3 Medium, the latest and most advanced text-to-image AI model in our Stable Diffusion 3 series! This new release represents a major milestone in the evolution of generative AI and continues our commitment to democratising this powerful technology. 🎉 Learn more and get started here:

Stability AI

307,838 次观看 • 2 年前

A new level of interactivity with Art. Pictures generated by #AI Stable Diffusion + Real time morph in #AR Invite me to an exhibition or something…

A new level of interactivity with Art. Pictures generated by #AI Stable Diffusion + Real time morph in #AR Invite me to an exhibition or something…

Sergei Galkin

382,582 次观看 • 3 年前

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

AK

83,657 次观看 • 3 年前

In this iteration, I’ve added AI at Meta’s SAM 2 to our workflow to segment people. Lisa and I had fun testing it in our lab—striking poses in sequence, with our bodies precisely isolated for a refined Stable Diffusion effect. #MR #AI #Passthrough Meta for Developers

In this iteration, I’ve added AI at Meta’s SAM 2 to our workflow to segment people. Lisa and I had fun testing it in our lab—striking poses in sequence, with our bodies precisely isolated for a refined Stable Diffusion effect. #MR #AI #Passthrough Meta for Developers

Hugues Bruyère

32,762 次观看 • 1 年前

Excited to share our interview with Sander Dieleman! This is Part 3 in our History of Diffusion series. We talk about diffusion as spectral autoregression, diffusion language models, flow matching, and much more. Enjoy!

Excited to share our interview with Sander Dieleman! This is Part 3 in our History of Diffusion series. We talk about diffusion as spectral autoregression, diffusion language models, flow matching, and much more. Enjoy!

Slater Stich

28,721 次观看 • 1 年前

Stable Diffusion 3.5 from Stability AI is now LIVE on Civitai! Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency. Generate with SD 3.5 Live on Civitai here👇🏽 All images used to create this video were generated with SD 3.5 by our community 🫶🏽

Stable Diffusion 3.5 from Stability AI is now LIVE on Civitai! Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency. Generate with SD 3.5 Live on Civitai here👇🏽 All images used to create this video were generated with SD 3.5 by our community 🫶🏽

Civitai

31,353 次观看 • 1 年前

Very excited to share our interview with Jascha Sohl-Dickstein on the history of diffusion models — from his original 2015 paper inventing them, to the GAN "ice age", to the resurgence in diffusion starting with DDPM. Enjoy!

Very excited to share our interview with Jascha Sohl-Dickstein on the history of diffusion models — from his original 2015 paper inventing them, to the GAN "ice age", to the resurgence in diffusion starting with DDPM. Enjoy!

Slater Stich

49,654 次观看 • 1 年前

Just found the dLLM library to create Diffusion Language Models It's still early but it's insanely fun to experiment with diffusion (training, inference, eval) dLLM has the potential of becoming the main library for diffusion LLMs

Just found the dLLM library to create Diffusion Language Models It's still early but it's insanely fun to experiment with diffusion (training, inference, eval) dLLM has the potential of becoming the main library for diffusion LLMs

Maxime Labonne

75,421 次观看 • 8 个月前

We’re excited to announce new editing features in Stable Assistant, our user-friendly chatbot. Leveraging the power of Stable Diffusion 3, these advanced text-to-image capabilities produce higher quality outputs. Explore all the features here:

We’re excited to announce new editing features in Stable Assistant, our user-friendly chatbot. Leveraging the power of Stable Diffusion 3, these advanced text-to-image capabilities produce higher quality outputs. Explore all the features here:

Stability AI

84,125 次观看 • 2 年前

Introducing InfiniteDiffusion, my independent paper accepted to #SIGGRAPH2026! I have one RTX 3090 Ti. No funding, advisors, or team. By day I'm a new grad SWE at Walmart. The paper has two main contributions: - InfiniteDiffusion: a new approach to infinite generation with diffusion models. - Terrain Diffusion: the world’s first learned procedural terrain generator. Here’s why this matters, and how they are connected. 🧵

Introducing InfiniteDiffusion, my independent paper accepted to #SIGGRAPH2026! I have one RTX 3090 Ti. No funding, advisors, or team. By day I'm a new grad SWE at Walmart. The paper has two main contributions: - InfiniteDiffusion: a new approach to infinite generation with diffusion models. - Terrain Diffusion: the world’s first learned procedural terrain generator. Here’s why this matters, and how they are connected. 🧵

Alexander Goslin

923,645 次观看 • 18 天前

Thanks to GPT-4, I've created a new plugin: StabilityGPT Now, you can run stable-diffusion directly in ChatGPT. 💬🎨 Imagine the possibilities!

Thanks to GPT-4, I've created a new plugin: StabilityGPT Now, you can run stable-diffusion directly in ChatGPT. 💬🎨 Imagine the possibilities!

Pietro Schirano

1,187,061 次观看 • 3 年前

Generative AI and WebAR are so powerful 🤩 In this experiment I used Stable Diffusion Depth2img, Three.js and 8thwall Visual Positioning System. #8thwall #niantic #stablediffusion #threejs

Generative AI and WebAR are so powerful 🤩 In this experiment I used Stable Diffusion Depth2img, Three.js and 8thwall Visual Positioning System. #8thwall #niantic #stablediffusion #threejs

Stijn Spanhove

113,955 次观看 • 3 年前

Hands-on Hallucination session: Focusing the diffusion process with the Hallucination Scope.⁣ Experimenting with new ways to explore and transform a scene.⁣ ⁣ #AI #StableDiffusion #Realtime

Hands-on Hallucination session: Focusing the diffusion process with the Hallucination Scope.⁣ Experimenting with new ways to explore and transform a scene.⁣ ⁣ #AI #StableDiffusion #Realtime

Hugues Bruyère

15,377 次观看 • 1 年前

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to 1280 x 2048 abs: project page:

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to 1280 x 2048 abs: project page:

AK

718,760 次观看 • 3 年前

🔱 Introducing Manta AI 🔱 In collaboration with Celestia, ORA, and Hyperbolic, we are excited to launch a comprehensive AI toolkit on #MantaPacific. Experience seamless training, deployment, and inference with our Universal Circuits, now enhanced with powerful AGI models like Stable Diffusion & Llama. 🌊 Dive into the future of AI on blockchain:

🔱 Introducing Manta AI 🔱 In collaboration with Celestia, ORA, and Hyperbolic, we are excited to launch a comprehensive AI toolkit on #MantaPacific. Experience seamless training, deployment, and inference with our Universal Circuits, now enhanced with powerful AGI models like Stable Diffusion & Llama. 🌊 Dive into the future of AI on blockchain:

Manta Network (🔱,🔱)

174,032 次观看 • 2 年前

100+ AI tools were released in the last 7 days. Here are the 5 best AI tools I found last week: 1. Stability AI Photoshop's AI plugin powered by Stable Diffusion. Helps you create, edit, and iterate AI images directly within Photoshop.

100+ AI tools were released in the last 7 days. Here are the 5 best AI tools I found last week: 1. Stability AI Photoshop's AI plugin powered by Stable Diffusion. Helps you create, edit, and iterate AI images directly within Photoshop.

Zain Kahn

1,039,650 次观看 • 3 年前

The folks Corridor combine Stable Diffusion, Dreambooth, and Davinci Resolve for their AI powered anime and the results are incredible!

The folks Corridor combine Stable Diffusion, Dreambooth, and Davinci Resolve for their AI powered anime and the results are incredible!

Ammaar Reshi

30,272,191 次观看 • 3 年前

I'm thrilled to announce the launch of ⚡️Flash Diffusion from Jasper! Earlier this year, with our acquisition of Clipdrop, we launched the Jasper AI Research Lab in Paris. Today, we are excited to release our first piece of groundbreaking research: the open-source distillation method, "Flash Diffusion". Flash Diffusion accelerates inference by 500%, reduces computing costs, and produces higher-quality image outputs. Dive into the details and discover how Flash Diffusion is set to revolutionize the field of AI and image synthesis. Read all about it here: Try a demo on Hugging Face:

I'm thrilled to announce the launch of ⚡️Flash Diffusion from Jasper! Earlier this year, with our acquisition of Clipdrop, we launched the Jasper AI Research Lab in Paris. Today, we are excited to release our first piece of groundbreaking research: the open-source distillation method, "Flash Diffusion". Flash Diffusion accelerates inference by 500%, reduces computing costs, and produces higher-quality image outputs. Dive into the details and discover how Flash Diffusion is set to revolutionize the field of AI and image synthesis. Read all about it here: Try a demo on Hugging Face:

Timothy Young

10,093 次观看 • 2 年前