Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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 görüntüleme • 1 yıl önce •via X (Twitter)

SanatBilim & TeknolojiEğitim
LIVE

Anya Rossi• Live Now

Private livecam show

6 Yorum

CodeRabbit profil fotoğrafı
CodeRabbit1 yıl önce

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

Purz.ai profil fotoğrafı
Purz.ai1 yıl önce

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

A.I.Warper profil fotoğrafı
A.I.Warper1 yıl önce

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

A.I.Warper profil fotoğrafı
A.I.Warper1 yıl önce

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) profil fotoğrafı
MemeCoinTracker (MCT)1 yıl önce

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

tarun bana profil fotoğrafı
tarun bana1 yıl önce

this is amazing, thank you.

Benzer Videolar

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 görüntüleme • 1 ay önce

MotionStreamer announced on Hugging Face Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space
0:40

MotionStreamer announced on Hugging Face Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space

AK

43,387 görüntüleme • 1 yıl önce

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

18,896 görüntüleme • 2 ay önce

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 görüntüleme • 6 ay önce

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

190,914 görüntüleme • 3 ay önce

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

82,137 görüntüleme • 3 yıl önce

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

10,681 görüntüleme • 5 ay önce

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

22,090 görüntüleme • 6 gün önce

Full video link in comment below
3:23

Full video link in comment below

Ajeet Bharti YouTube

19,304 görüntüleme • 9 ay önce

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

22,186 görüntüleme • 1 yıl önce

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

24,086 görüntüleme • 2 ay önce

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

279,938 görüntüleme • 2 yıl önce

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

59,423 görüntüleme • 3 ay önce

'Diversity is nice... to visit." Link to the full thing in the replies below! 👇
1:01

'Diversity is nice... to visit." Link to the full thing in the replies below! 👇

Edward Dutton

22,258 görüntüleme • 2 ay önce

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 görüntüleme • 1 yıl önce

This is your chance to get 50% off a Real Vision Connect membership. Link in comment below...
0:22

This is your chance to get 50% off a Real Vision Connect membership. Link in comment below...

Raoul Pal

58,208 görüntüleme • 10 ay önce

FLUX.2 Klein in pure pixel space! No VAE. AsymFlow - hyper-realistic images by working directly in pixel space rather than using compressed latent representations. - sharper textures, superior visual fidelity - 40% faster - low-rank noise parameterization to solve high-dimensional bottlenecks ComfyUI support incoming
0:42

FLUX.2 Klein in pure pixel space! No VAE. AsymFlow - hyper-realistic images by working directly in pixel space rather than using compressed latent representations. - sharper textures, superior visual fidelity - 40% faster - low-rank noise parameterization to solve high-dimensional bottlenecks ComfyUI support incoming

Wildminder

27,210 görüntüleme • 1 ay önce

Face Replacement and De-aging Demo: VFX artist Doug Hogan built a fully automated face swap workflow inside ComfyUI. Florence 2 → SAM2 → WAN Video. One pipeline. Temporally consistent across every frame. Not a pixel swap. The workflow detects the head, segments it, drives motion from the original performance, and uses a reference image + auto prompt to transfer the identity while preserving lighting and timing. Face replacement. De-aging. All inside ComfyUI. Click the link below for the workflow 👇
4:13

Face Replacement and De-aging Demo: VFX artist Doug Hogan built a fully automated face swap workflow inside ComfyUI. Florence 2 → SAM2 → WAN Video. One pipeline. Temporally consistent across every frame. Not a pixel swap. The workflow detects the head, segments it, drives motion from the original performance, and uses a reference image + auto prompt to transfer the identity while preserving lighting and timing. Face replacement. De-aging. All inside ComfyUI. Click the link below for the workflow 👇

ComfyUI

13,948 görüntüleme • 16 gün önce