正在加载视频...

视频加载失败

返回首页

Object Relighting with Latent Bridge Matching Link to Hugging Face space below + Link to Kijai's ComfyUI wrapper in first comment 👇

AIWarper's profile picture

A.I.Warper

32,753 subscribers

17,893 次观看 • 1 年前 •via X (Twitter)

艺术科学技术教育
LIVE

Anya Rossi• Live Now

Private livecam show

6 条评论

CodeRabbit 的头像
CodeRabbit1 年前

AI-first pull request reviewer with context-aware feedback, line-by-line code suggestions, and real-time chat.

Purz.ai 的头像
Purz.ai1 年前

Imagine being excited for normal crafter for re-lighting just to have this come out a few days later 🤗

A.I.Warper 的头像
A.I.Warper1 年前

I’ve not seen anyone use this with video yet though

A.I.Warper 的头像
A.I.Warper1 年前

It’s worth noting that this repo also has checkpoints and inference code for: Normals approximation Depth approximation Object removal (given a mask)

MemeCoinTracker (MCT) 的头像
MemeCoinTracker (MCT)1 年前

Whoa, just had a major insight! Latent bridge matching = alpha move! Can't wait to see what's lit with this tech

tarun bana 的头像
tarun bana1 年前

this is amazing, thank you.

相关视频

Create transformation videos where a cube, sphere, capsule, or custom object transforms into a person or item with a button press using Seedance 2.0 inside ComfyUI. The workflow automatically generates matching first and last frames while keeping the environment and style consistent throughout the effect. Try the workflow, link below.
1:11

Create transformation videos where a cube, sphere, capsule, or custom object transforms into a person or item with a button press using Seedance 2.0 inside ComfyUI. The workflow automatically generates matching first and last frames while keeping the environment and style consistent throughout the effect. Try the workflow, link below.

ComfyUI

20,405 次观看 • 4 个月前

A look at the video outpainting workflow in ComfyUI using LTX 2.3. 🎥 Instead of cropping your 16:9 footage for vertical, use this IC-LoRA setup to generate the missing space and keep your original frame. Shout out to Mohamed Oumoumad for their open source contribution. Link to workflow below! 👇
0:49

A look at the video outpainting workflow in ComfyUI using LTX 2.3. 🎥 Instead of cropping your 16:9 footage for vertical, use this IC-LoRA setup to generate the missing space and keep your original frame. Shout out to Mohamed Oumoumad for their open source contribution. Link to workflow below! 👇

ComfyUI

19,041 次观看 • 5 个月前

I wanted to try out Mickmumpitz ComfyUI workflow that lets you animate movement by manually shifting objects or images in the scene. Link to his tutorial below 👇
0:29

I wanted to try out Mickmumpitz ComfyUI workflow that lets you animate movement by manually shifting objects or images in the scene. Link to his tutorial below 👇

enigmatic_e

324,989 次观看 • 9 个月前

Cohere transcribe Sota open source transcription model running in the browser :) Weights on Hugging Face link below
0:36

Cohere transcribe Sota open source transcription model running in the browser :) Weights on Hugging Face link below

Nick Frosst

191,513 次观看 • 6 个月前

try out the Gradio Demo for AudioLDM: Text-to-Audio Generation with Latent Diffusion Models on Hugging Face demo:
1:36

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

AK

82,138 次观看 • 3 年前

Introducing Print Spaces First space to launch binder Now you can customize a layout that best serves your printworld needs Binder Space now live - link below 👇
0:30

Introducing Print Spaces First space to launch binder Now you can customize a layout that best serves your printworld needs Binder Space now live - link below 👇

print.world

10,784 次观看 • 7 个月前

A conversation is all it takes to launch powerful ComfyUI workflows. This showcase demonstrates how Comfy MCP can generate, refine, and iterate on creative assets using natural language. To try this workflow, link below 👇
1:19

A conversation is all it takes to launch powerful ComfyUI workflows. This showcase demonstrates how Comfy MCP can generate, refine, and iterate on creative assets using natural language. To try this workflow, link below 👇

ComfyUI

10,870 次观看 • 3 个月前

Bring your Favourite models to Comfy Cloud ☁️ Now you can import models from Civitai or Hugging Face with a single paste of the link. No more manual downloads or file management. We will handle the rest! Try it out in Comfy Cloud today!
0:43

Bring your Favourite models to Comfy Cloud ☁️ Now you can import models from Civitai or Hugging Face with a single paste of the link. No more manual downloads or file management. We will handle the rest! Try it out in Comfy Cloud today!

ComfyUI

10,909 次观看 • 8 个月前

Do you Wanna trade without using your own money? Bitunix is giving up to $400 in bonuses for first-time deposits. I'm giving 30 VIP signal slots to people ready to flip it. Comment “TRADING” to join. First come, first served. Sign up with my link below to qualify 👇
0:53

Do you Wanna trade without using your own money? Bitunix is giving up to $400 in bonuses for first-time deposits. I'm giving 30 VIP signal slots to people ready to flip it. Comment “TRADING” to join. First come, first served. Sign up with my link below to qualify 👇

Damilare Samuel (Quiv)

26,056 次观看 • 1 年前

MiniMax H3 is open weights and native in ComfyUI. MiniMax (official) H3 has text, images, video, and audio in one model, video and stereo audio out in a single pass, running locally or on Comfy Cloud. To try this workflow, link below 👇
0:43

MiniMax H3 is open weights and native in ComfyUI. MiniMax (official) H3 has text, images, video, and audio in one model, video and stereo audio out in a single pass, running locally or on Comfy Cloud. To try this workflow, link below 👇

ComfyUI

12,740 次观看 • 1 个月前

One animation. Different visual styles. This workflow uses Seedance 2.0 in ComfyUI with reference images to explore different looks while preserving the same motion and camera movement. In this example, the animation starts with a simple Blender scene, making it easy to compare different creative directions. Featured clips courtesy of A.I.Warper, Reid Hannaford, and JMS.vid. To try this workflow, link below 👇
1:25

One animation. Different visual styles. This workflow uses Seedance 2.0 in ComfyUI with reference images to explore different looks while preserving the same motion and camera movement. In this example, the animation starts with a simple Blender scene, making it easy to compare different creative directions. Featured clips courtesy of A.I.Warper, Reid Hannaford, and JMS.vid. To try this workflow, link below 👇

ComfyUI

24,211 次观看 • 3 个月前

A fun AI video effect: ride a living animal like it's a skateboard. This ComfyUI workflow uses an LLM to generate optimized Seedance prompts, making the effect easy to recreate without all the prompt tweaking. To try this workflow, link below 👇
1:40

A fun AI video effect: ride a living animal like it's a skateboard. This ComfyUI workflow uses an LLM to generate optimized Seedance prompts, making the effect easy to recreate without all the prompt tweaking. To try this workflow, link below 👇

ComfyUI

11,175 次观看 • 2 个月前

A fun AI video effect to try: balance on top of a moving animal while pulling off impossible tricks. This ComfyUI workflow uses an LLM to generate the right Seedance 2.0 prompts, making it easy to recreate this viral-style effect with smooth, consistent results. To try this workflow, link below 👇
0:22

A fun AI video effect to try: balance on top of a moving animal while pulling off impossible tricks. This ComfyUI workflow uses an LLM to generate the right Seedance 2.0 prompts, making it easy to recreate this viral-style effect with smooth, consistent results. To try this workflow, link below 👇

ComfyUI

120,259 次观看 • 2 个月前

CODEX 1 is LIVE! Comment 🔑 for Access Code. 👇 Use the link below to access the experience.
0:20

CODEX 1 is LIVE! Comment 🔑 for Access Code. 👇 Use the link below to access the experience.

Rogues

22,193 次观看 • 1 年前

This viral “inflation effect” by Ingi Erlingsson 🪄 gained significant traction across feeds. Here’s how to recreate it in ComfyUI using a streamlined node-based workflow. Click the link below for the full workflow ↓
0:43

This viral “inflation effect” by Ingi Erlingsson 🪄 gained significant traction across feeds. Here’s how to recreate it in ComfyUI using a streamlined node-based workflow. Click the link below for the full workflow ↓

ComfyUI

24,260 次观看 • 6 个月前

The DarkSide of Trading: Full Interview Premieres Feb 21st - 2pm UK time. To be in with a chance to win Free PTL Membership simply comment; "Waiting" in the comments section on the YT video. YT video link below 👇 👇 👇
0:22

The DarkSide of Trading: Full Interview Premieres Feb 21st - 2pm UK time. To be in with a chance to win Free PTL Membership simply comment; "Waiting" in the comments section on the YT video. YT video link below 👇 👇 👇

PTL | Pro Traders Lounge

279,942 次观看 • 2 年前

BIG DROP ALERT 🚨 Kling 3.0 is officially on BigMotion and it goes CRAZY Dropping 15 FREE SUBS to celebrate — here's how to get one: - like, repost & follow - comment with what you'd gen first with Kling 3.0 Winners in 6 hours ⏰ don't sleep Link below 👇
0:30

BIG DROP ALERT 🚨 Kling 3.0 is officially on BigMotion and it goes CRAZY Dropping 15 FREE SUBS to celebrate — here's how to get one: - like, repost & follow - comment with what you'd gen first with Kling 3.0 Winners in 6 hours ⏰ don't sleep Link below 👇

BigMotion.ai

59,588 次观看 • 6 个月前

Today, a new interview with Lue Elizondo claims he and "UFO whistleblower" David Grusch worked together at U.S. Space Force on UAPs, funded by USSF, with data surpassing what he collected with AATIP. I have reached out to Space Force for comment. (Link below)
0:55

Today, a new interview with Lue Elizondo claims he and "UFO whistleblower" David Grusch worked together at U.S. Space Force on UAPs, funded by USSF, with data surpassing what he collected with AATIP. I have reached out to Space Force for comment. (Link below)

John Greenewald, Jr.

118,605 次观看 • 1 年前