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.

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.... show more

Stability AI

257,298 subscribers

307,838 views • 2 years ago •via X (Twitter)

Science & Technology News & Politics

Anya Rossi• Live Now

Private livecam show

10 Comments

hoblin 🇺🇦🇫🇮2 years ago

I’m wondering why don’t you post some real images by released SD3? Not by the model that wasn’t lobotomised and is kept inside.

@AI_EmeraldApple2 years ago

unfortuanately it looks like it's censored worse than SDXL or stable cascade was

Kenny Le2 years ago

By making these advanced text-to-image AI models more accessible, you’re opening up incredible possibilities for creators everywhere. Congratulations on this achievement!

BAIJ2 years ago

Great! @huggingface please get diffusers updated!

Dreaming Tulpa 🥓👑2 years ago

Finally 🥳 thanks for the weights 🙏🔥

ijohn2 years ago

It is troubling that SD3 is so bad; generating images without distortion is a feat :/

Bijoux 2too2 years ago

@pharmapsychotic Congratulations and historic day 🙌🏽

trod roughshod 🇮🇱2 years ago

Soon we'll see how much better SD3 Medium is as a base model compared to SDXL.

Jasmin Hydra2 years ago

I cannot believe how many H100 hours were wastet to train this censored model which can not even draw hands.

Reza Sayar2 years ago

HOW DAFAQ IS THIS YOUR MOST ADVANCED MODEL IF YOU HAVE WAY LARGER ONES THAT ARE NOT OPEN WEIGHT?!

Related Videos

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Stability AI

1,024,438 views • 2 years ago

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 views • 2 years ago

Today we are announcing Stable Artisan, bringing the capabilities of Stability AI’s Developer Platform API accessible to a wider audience. Featuring our advanced models such as Stable Diffusion 3, Stable Video, and Stable Image Core, Stable Artisan enables users to create high-quality media directly within Discord. Join the server and get started here: Read our blog here:

Today we are announcing Stable Artisan, bringing the capabilities of Stability AI’s Developer Platform API accessible to a wider audience. Featuring our advanced models such as Stable Diffusion 3, Stable Video, and Stable Image Core, Stable Artisan enables users to create high-quality media directly within Discord. Join the server and get started here: Read our blog here:

Stability AI

185,446 views • 2 years ago

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

10,091 views • 2 years ago

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

31,235 views • 1 year ago

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 ⬇️

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

128,697 views • 2 years ago

🚀 First Update of LTX-Video is Here! We’re thrilled to announce the release of LTX-Video 0.9.1, the latest version of our generative AI video model! This update is packed with upgrades that make video creation smoother, faster, and more impressive than ever. Here’s what’s new 👇

🚀 First Update of LTX-Video is Here! We’re thrilled to announce the release of LTX-Video 0.9.1, the latest version of our generative AI video model! This update is packed with upgrades that make video creation smoother, faster, and more impressive than ever. Here’s what’s new 👇

Yoav HaCohen

18,007 views • 1 year ago

We’re introducing major updates to Gemini in @GoogleChrome for MacOS, Windows and Chromebook Plus. Built on Gemini 3, our most intelligent model, these powerful new AI features can help you multitask more easily and get the most out of the web 🧵

We’re introducing major updates to Gemini in @GoogleChrome for MacOS, Windows and Chromebook Plus. Built on Gemini 3, our most intelligent model, these powerful new AI features can help you multitask more easily and get the most out of the web 🧵

Google

2,158,347 views • 5 months ago

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 views • 3 years ago

We're thrilled to announce the release of SRI 1.0.0 - the most important milestone in our Stratum V2 journey🎉 New release stands ready for immediate testing and integration. 🔗 🚀

We're thrilled to announce the release of SRI 1.0.0 - the most important milestone in our Stratum V2 journey🎉 New release stands ready for immediate testing and integration. 🔗 🚀

Stratum V2

60,245 views • 2 years ago

Evolution of Humanity using Stable Diffusion (AI)

Evolution of Humanity using Stable Diffusion (AI)

Evolution Of Life

96,616 views • 2 years ago

In Prompt Engineering for Vision Models, taught by Abby Jacques Verre and Caleb Kaiser of Comet , you’ll learn how to prompt and fine-tune vision models for personalized image generation, image editing, object detection and segmentation. The prompts you'll use for vision models could be text, point coordinates, or bounding boxes, depending on the model. You'll also learn to tune hyperparameters to shape the output. Models you'll use include Segment-Anything Model (SAM), OWL-ViT, and Stable Diffusion. You'll also learn to fine-tune Stable Diffusion to generate personalized images (say, an image of a specific person), using a handful of images for training. As an example of a multi-step workflow, you'll use OWL-ViT to detect an object based on a text prompt, then pass the bounding box to SAM to create a segmentation mask, and input that mask into Stable Diffusion to replace the original object with a new one based on a text prompt. Controlling vision models can be tricky; this course will teach prompting and fine-tuning techniques to get precise control over their output. Get started here:

In Prompt Engineering for Vision Models, taught by Abby Jacques Verre and Caleb Kaiser of Comet , you’ll learn how to prompt and fine-tune vision models for personalized image generation, image editing, object detection and segmentation. The prompts you'll use for vision models could be text, point coordinates, or bounding boxes, depending on the model. You'll also learn to tune hyperparameters to shape the output. Models you'll use include Segment-Anything Model (SAM), OWL-ViT, and Stable Diffusion. You'll also learn to fine-tune Stable Diffusion to generate personalized images (say, an image of a specific person), using a handful of images for training. As an example of a multi-step workflow, you'll use OWL-ViT to detect an object based on a text prompt, then pass the bounding box to SAM to create a segmentation mask, and input that mask into Stable Diffusion to replace the original object with a new one based on a text prompt. Controlling vision models can be tricky; this course will teach prompting and fine-tuning techniques to get precise control over their output. Get started here:

Andrew Ng

151,198 views • 2 years ago

This is a big day. Meta is open-sourcing AudioCraft. You can now generate incredible music and sounds with a single prompt. It includes the most performant Generative AI Model (audio) on the market, the "Llama" of Audio. The research framework contains the weights and code of these models: ▸ MusicGen: controllable text-to-music model. ▸ AudioGen: text-to-sound model. ▸ EnCodec: high fidelity neural audio codec. ▸ Multi Band Diffusion: An EnCodec compatible decoder using diffusion. This is going to tremendously speed up audio research 👏

This is a big day. Meta is open-sourcing AudioCraft. You can now generate incredible music and sounds with a single prompt. It includes the most performant Generative AI Model (audio) on the market, the "Llama" of Audio. The research framework contains the weights and code of these models: ▸ MusicGen: controllable text-to-music model. ▸ AudioGen: text-to-sound model. ▸ EnCodec: high fidelity neural audio codec. ▸ Multi Band Diffusion: An EnCodec compatible decoder using diffusion. This is going to tremendously speed up audio research 👏

Lior Alexander

231,604 views • 2 years ago

We created a series of simplified notebooks that cover essential aspects of Stable Diffusion, using the vanilla Stable Diffusion 2.1 base to utilise it as a face-editing model for building your own face app 🧵(1/3) Github :

We created a series of simplified notebooks that cover essential aspects of Stable Diffusion, using the vanilla Stable Diffusion 2.1 base to utilise it as a face-editing model for building your own face app 🧵(1/3) Github :

OutofAi

45,864 views • 2 years ago

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

718,746 views • 3 years ago

Today we’re sharing two new advances in our generative AI research: Emu Video & Emu Edit. Details ➡️ These new models deliver exciting results in high quality, diffusion-based text-to-video generation & controlled image editing w/ text instructions. 🧵

Today we’re sharing two new advances in our generative AI research: Emu Video & Emu Edit. Details ➡️ These new models deliver exciting results in high quality, diffusion-based text-to-video generation & controlled image editing w/ text instructions. 🧵

AI at Meta

798,207 views • 2 years ago

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 views • 1 year ago

Stable Diffusion generates beautiful images, but can it be used for open-world recognition? Try Demo! Our #CVPR2023 paper shows that the pre-trained diffusion model indeed is a good image parser, allows for open-vocabulary segmentation and detection.

Stable Diffusion generates beautiful images, but can it be used for open-world recognition? Try Demo! Our #CVPR2023 paper shows that the pre-trained diffusion model indeed is a good image parser, allows for open-vocabulary segmentation and detection.

Xiaolong Wang

241,225 views • 3 years ago

(1/10) 🔥Thrilled to introduce OneDiffusion—our latest work in unified diffusion modeling! 🚀 This model bridges the gap between image synthesis and understanding, excelling in a wide range of tasks: T2I, conditional generation, image understanding, identity preservation, multiview generation, and even camera pose estimation. Learn more at: Project: arXiv: Code (on the way):

(1/10) 🔥Thrilled to introduce OneDiffusion—our latest work in unified diffusion modeling! 🚀 This model bridges the gap between image synthesis and understanding, excelling in a wide range of tasks: T2I, conditional generation, image understanding, identity preservation, multiview generation, and even camera pose estimation. Learn more at: Project: arXiv: Code (on the way):

Jiasen Lu

33,383 views • 1 year ago

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 views • 1 year ago