正在加载视频...

视频加载失败

返回首页

Semi-realtime Stable Diffusion image-to-image (Van Gogh style), Unity plugin based on Apple's Core ML port. The latency is about 2 seconds on M1 Max MacBook Pro.

_kzr's profile picture

Keijiro Takahashi

59,059 subscribers

291,867 次观看 • 3 年前 •via X (Twitter)

艺术科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

10 条评论

Sean 的头像
Sean3 年前

Nice! Reminds me of this little experiment I did with minecraft - got it running as a mirror (2-3 second delay on 3090)

Grig ₡🌱 的头像
Grig ₡🌱3 年前

This is awesome! Can you pass the scene camera to it?

Keijiro Takahashi 的头像
Keijiro Takahashi3 年前

The repository contains it.

BLENDER SUSHI 🫶 X - 24/7 Blenderian 的头像
BLENDER SUSHI 🫶 X - 24/7 Blenderian3 年前

I cloned the plugin and CoreML, but not sure how to use it inside Unity Project. I could not find example project. I asked on Github, maybe there are extra steps or I miss to find anything to get this running?

Dreaming Tulpa 🥓👑 的头像
Dreaming Tulpa 🥓👑3 年前

Nice one, gonna put this into

IF 的头像
IF3 年前

Bravo, that's some unity next level dev skills, got diffusion inside unity with almost rt cam control feedback on an M1

Alchymi 的头像
Alchymi3 年前

Didn't parse the git, did you tryed it with ControlNet ?

Zilu 的头像
Zilu3 年前

@bigheeno

Mike 的头像
Mike3 年前

Will this run on my ipad air M1 ?

Laurence Bremner 的头像
Laurence Bremner3 年前

We'll soon have AI transforming our dull selfies into masterpieces 🤔

相关视频

HOLY SMOKES! Apple's new MacBook Neo with the A18 Pro iPhone chip can actually handle 3D video rendering in Blender! It's over TWICE as fast as the M1 MacBook Air! Full Neo vs M1 Air comparison video is LIVE on YouTube:
0:42

HOLY SMOKES! Apple's new MacBook Neo with the A18 Pro iPhone chip can actually handle 3D video rendering in Blender! It's over TWICE as fast as the M1 MacBook Air! Full Neo vs M1 Air comparison video is LIVE on YouTube:

Vadim Yuryev

591,042 次观看 • 2 个月前

Apple M1 Pro vs M4 Max compiling the same Spring Boot & Vaadin app to a GraalVM native image.
0:31

Apple M1 Pro vs M4 Max compiling the same Spring Boot & Vaadin app to a GraalVM native image.

Marcus Hellberg

32,461 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 🫶🏽
0:25

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

31,233 次观看 • 1 年前

New paper from Apple - Sharp Monocular View Synthesis in Less than a Second Mescheder et al. @ Apple just released a very impressive paper (congrats! 🎉🥳). You give it an image and it generates a really great looking 3d Gaussian representation. Uses depth pro. It's really good. The model is about 3GB, and takes ~5-10s on my M1 Max per image. Single feedforward pass network. The video is using "Metal Splatter" to view the .ply from ml-sharp on Apple Vision Pro. Some really wow moments today trying it on different scenes.
0:22

New paper from Apple - Sharp Monocular View Synthesis in Less than a Second Mescheder et al. @ Apple just released a very impressive paper (congrats! 🎉🥳). You give it an image and it generates a really great looking 3d Gaussian representation. Uses depth pro. It's really good. The model is about 3GB, and takes ~5-10s on my M1 Max per image. Single feedforward pass network. The video is using "Metal Splatter" to view the .ply from ml-sharp on Apple Vision Pro. Some really wow moments today trying it on different scenes.

Tim Davison ᯅ

132,673 次观看 • 5 个月前

DiffusionKit now supports Stable Diffusion 3 Medium MLX Python and Core ML Swift Inference work great for on-device inference on Mac! MLX: Core ML: Mac App: Hugging Face Diffusers App (Pending App Store review)
0:20

DiffusionKit now supports Stable Diffusion 3 Medium MLX Python and Core ML Swift Inference work great for on-device inference on Mac! MLX: Core ML: Mac App: Hugging Face Diffusers App (Pending App Store review)

argmax

73,996 次观看 • 2 年前

DiffSplat Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation DiffSplat is a generative framework to synthesize 3D Gaussian Splats from text prompts & single-view images in ⚡️ 1~2 seconds. It is fine-tuned directly from a pretrained text-to-image diffusion model.
0:24

DiffSplat Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation DiffSplat is a generative framework to synthesize 3D Gaussian Splats from text prompts & single-view images in ⚡️ 1~2 seconds. It is fine-tuned directly from a pretrained text-to-image diffusion model.

AK

38,416 次观看 • 1 年前

Le nouveau MacBook Pro M5 Pro/Max a été annoncé ! → Je me le prends ou pas ? 🤔 (je suis sous MacBook Pro M1 Max)
1:40

Le nouveau MacBook Pro M5 Pro/Max a été annoncé ! → Je me le prends ou pas ? 🤔 (je suis sous MacBook Pro M1 Max)

Basti Ui ✌️

38,114 次观看 • 3 个月前

I tried out that newly released Apple “single image to gaussian splat” model today It’s actually incredible. Unlike the current spatial scenes feature, you can actually WALK INTO the memory you captured on your phone It only took about 10 seconds on my MacBook Pro to generate
0:49

I tried out that newly released Apple “single image to gaussian splat” model today It’s actually incredible. Unlike the current spatial scenes feature, you can actually WALK INTO the memory you captured on your phone It only took about 10 seconds on my MacBook Pro to generate

Brad Lynch

622,996 次观看 • 5 个月前

In addition to presets, dedicated outpainting is now live in the Stable Diffusion #Photoshop plugin!
0:28

In addition to presets, dedicated outpainting is now live in the Stable Diffusion #Photoshop plugin!

Christian Cantrell

74,686 次观看 • 3 年前

Image. Then motion. GPT Image 2 + Seedance 2.0 are now both live on Pollo AI. GPT Image 2 → structured layouts, sharp text, consistent characters — ready for ads, products, and social content. Seedance 2.0 → cinematic, stable, smooth video — straight from your image. From image to motion, the workflow is fast, seamless, and powerful.
0:20

Image. Then motion. GPT Image 2 + Seedance 2.0 are now both live on Pollo AI. GPT Image 2 → structured layouts, sharp text, consistent characters — ready for ads, products, and social content. Seedance 2.0 → cinematic, stable, smooth video — straight from your image. From image to motion, the workflow is fast, seamless, and powerful.

Pollo AI

430,419 次观看 • 1 个月前

This, my friends is Ubuntu running on bare metal on an M1 Pro MacBook Pro, Pro. (To my Apple Fanboys… GET REKT LOSERS!!!) 😎 mRr3b00t
0:32

This, my friends is Ubuntu running on bare metal on an M1 Pro MacBook Pro, Pro. (To my Apple Fanboys… GET REKT LOSERS!!!) 😎 mRr3b00t

Denver Coder

1,132,878 次观看 • 2 年前

Running Qwen3.6 35B (vision) on 2 x M5 Max MacBook Pro with RDMA over Thunderbolt 5. It describes the image and identifies Apple Park correctly, but misidentifies John Ternus as Jeff Williams. Near instant response with prefix caching.
0:28

Running Qwen3.6 35B (vision) on 2 x M5 Max MacBook Pro with RDMA over Thunderbolt 5. It describes the image and identifies Apple Park correctly, but misidentifies John Ternus as Jeff Williams. Near instant response with prefix caching.

Alex Cheema

99,474 次观看 • 1 个月前

🤯 You can now easily face-swap any video, all locally on your Macbook. All you need is a photo and a video. FaceFusion is an open-source face swapper/enhancer with a simple web interface. On an M1/M2 Macbook, it even makes use of Core ML!
0:27

🤯 You can now easily face-swap any video, all locally on your Macbook. All you need is a photo and a video. FaceFusion is an open-source face swapper/enhancer with a simple web interface. On an M1/M2 Macbook, it even makes use of Core ML!

Marcel Pociot 🧪

206,209 次观看 • 2 年前

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.
0:22

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

AK

16,062 次观看 • 1 年前

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:
0:30

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

184,575 次观看 • 2 年前

I chopped the head off a broken screen'd M1 Max MacBook Pro to become a fancy keyboard with a mobile compute powerhouse for Vision Pro
0:47

I chopped the head off a broken screen'd M1 Max MacBook Pro to become a fancy keyboard with a mobile compute powerhouse for Vision Pro

Brad Lynch

3,156,600 次观看 • 2 年前

My canvas based AI image generation tool is live! It's built on top of tldraw and uses Nano Banana Pro for image generation. You can sketch, annotate, collage in a frame... And then click to generate an image. Check it out 👉
1:00

My canvas based AI image generation tool is live! It's built on top of tldraw and uses Nano Banana Pro for image generation. You can sketch, annotate, collage in a frame... And then click to generate an image. Check it out 👉

Charlie Clark

44,335 次观看 • 6 个月前

ComfyUI SeeThrough Plugin - A port of the SeeThrough project into ComfyUI. Splits a single 2D character image into individual components — from eyes and hair to limbs — enabling single-image decomposition for Live2D rigs.
1:37

ComfyUI SeeThrough Plugin - A port of the SeeThrough project into ComfyUI. Splits a single 2D character image into individual components — from eyes and hair to limbs — enabling single-image decomposition for Live2D rigs.

jtydhr88

77,319 次观看 • 2 个月前

Apple's M5 Pro absolutely DESTROYS the new Intel Panther Lake X7-358H chip! Here's photo editing in Lightroom Classic. 2-3x faster based on the number of photos exported. Watch the full $2700 M5 Pro 16" MacBook Pro vs $2400 Galaxy Book6 Ultra video now:
1:22

Apple's M5 Pro absolutely DESTROYS the new Intel Panther Lake X7-358H chip! Here's photo editing in Lightroom Classic. 2-3x faster based on the number of photos exported. Watch the full $2700 M5 Pro 16" MacBook Pro vs $2400 Galaxy Book6 Ultra video now:

Vadim Yuryev

36,359 次观看 • 2 个月前

the best part about a MacBook is that it delivers the same level of performance even on battery, which Windows laptops can never $4400 MacBook Pro vs $11,000 DELL Pro Max btw (via MaxTech)
0:42

the best part about a MacBook is that it delivers the same level of performance even on battery, which Windows laptops can never $4400 MacBook Pro vs $11,000 DELL Pro Max btw (via MaxTech)

Dipayan Ray

40,310 次观看 • 2 个月前