Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

added sliding sampling [as in comfyui] to animatediff and zeroscope on

eps696's profile picture

vadim epstein

2,312 subscribers

62,214 Aufrufe • vor 2 Jahren •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

9 Kommentare

Profilbild von vadim epstein
vadim epsteinvor 2 Jahren

one more, with dramatic edits

Profilbild von Retropunk
Retropunkvor 2 Jahren

Lost footage from tornado scene in Wizard of Oz? Dope!

Profilbild von Infinite Vibes
Infinite Vibesvor 2 Jahren

Infinite Zeroscope!? Wonderful, thank you.

Profilbild von vadim epstein
vadim epsteinvor 2 Jahren

both zeroscope and animdiff use the same unet3D backbone, so that [sliding window] sampling trick from comfyui works equally with both

Profilbild von Nathan Shipley
Nathan Shipleyvor 2 Jahren

Awesome, Vadim 🙌

Profilbild von vadim epstein
vadim epsteinvor 2 Jahren

thank you sir

Profilbild von Andrey Flat
Andrey Flatvor 2 Jahren

oooooooooooooooooooffffffffff

Profilbild von Orb
Orbvor 2 Jahren

ocean, no, fluid simulation, wait fire, no fur? character! ah no waves, sprites? wait morphing, water? no. ah fuck ok i give up.

Profilbild von Krzysztof Gonia
Krzysztof Goniavor 2 Jahren

Good enough to be used in music videos. Nice.

Ähnliche Videos

The before and after of this video. Top is ViggleAI and the bottom is it being ran through Animatediff in ComfyUI
0:22

The before and after of this video. Top is ViggleAI and the bottom is it being ran through Animatediff in ComfyUI

enigmatic_e

65,203 Aufrufe • vor 2 Jahren

Experimenting with new audio reactive nodes by @yvann_mp4 in ComfyUI has lead me here. Probably still just a proof of concept, but loving what is possible. #ai #comfyui #animatediff #ipadapter
0:45

Experimenting with new audio reactive nodes by @yvann_mp4 in ComfyUI has lead me here. Probably still just a proof of concept, but loving what is possible. #ai #comfyui #animatediff #ipadapter

VISUAL FRISSON

18,098 Aufrufe • vor 1 Jahr

Video to 70's Cartoon AI exploration. Created with #AnimateDiff and #IPAdapter to stylize input video for a retro cartoon look. 🎥 Result (10fps) vs input (30fps iPhone footage) #aivideo #stablediffusion #ComfyUI More imagery (and result video by itself) in thread!🧵
0:40

Video to 70's Cartoon AI exploration. Created with #AnimateDiff and #IPAdapter to stylize input video for a retro cartoon look. 🎥 Result (10fps) vs input (30fps iPhone footage) #aivideo #stablediffusion #ComfyUI More imagery (and result video by itself) in thread!🧵

Nathan Shipley

233,679 Aufrufe • vor 2 Jahren

Testing LCM LORAs in an AnimateDiff & multi-controlnet workflow in ComfyUI. I was able to process this entire Black Pink music video as a single .mp4 input. The LCM lets me render at 6 steps (vs 20+) on my 4090 and uses up only 10.5 GB of VRAM. Here's a breakdown 🧵[1/11]
3:25

Testing LCM LORAs in an AnimateDiff & multi-controlnet workflow in ComfyUI. I was able to process this entire Black Pink music video as a single .mp4 input. The LCM lets me render at 6 steps (vs 20+) on my 4090 and uses up only 10.5 GB of VRAM. Here's a breakdown 🧵[1/11]

CoffeeVectors

182,428 Aufrufe • vor 2 Jahren

1-Click WAN with ComfyUI Locally Wrote some automation scripts to 1-click download the workflows and models to the correct places as explained in this blog post and.... it just works! Thank you ComfyUI. Just published so anyone can instantly get started with WAN on ComfyUI.
1:23

1-Click WAN with ComfyUI Locally Wrote some automation scripts to 1-click download the workflows and models to the correct places as explained in this blog post and.... it just works! Thank you ComfyUI. Just published so anyone can instantly get started with WAN on ComfyUI.

cocktail peanut

23,292 Aufrufe • vor 1 Jahr

ATI Trajectory Control just landed on Comfy Cloud thanks to Fill 🚀 Animate still photos in seconds—pin your subject, draw a line, done. The easiest way yet to get that wild sliding-background look.
4:36

ATI Trajectory Control just landed on Comfy Cloud thanks to Fill 🚀 Animate still photos in seconds—pin your subject, draw a line, done. The easiest way yet to get that wild sliding-background look.

ComfyUI

12,703 Aufrufe • vor 8 Monaten

Artistic calligraphy being added to a Japanese restaurant’s sliding door
0:45

Artistic calligraphy being added to a Japanese restaurant’s sliding door

Massimo

17,508 Aufrufe • vor 8 Monaten

It's been a crazy couple of days, trying all sorts of things with ComfyUI + AnimateDiff-Evolved and various ControlNets. I'm absolutely blown away by the consistency and clarity of the animations using this method. Workflow below 👇
1:08

It's been a crazy couple of days, trying all sorts of things with ComfyUI + AnimateDiff-Evolved and various ControlNets. I'm absolutely blown away by the consistency and clarity of the animations using this method. Workflow below 👇

Purz.ai

49,496 Aufrufe • vor 2 Jahren

Some experiments I'm working on to explore ways to improve the 2D workflow in Grease Pencil using ComfyuI in Blender to redraw based on perspective. For now, these are just experiments, not an available add-on :( #GreasePencil #Blender #2d #ComfyUI
1:38

Some experiments I'm working on to explore ways to improve the 2D workflow in Grease Pencil using ComfyuI in Blender to redraw based on perspective. For now, these are just experiments, not an available add-on :( #GreasePencil #Blender #2d #ComfyUI

Daniel Martínez Lara 🔶

30,814 Aufrufe • vor 6 Monaten

ComfyUI just added OpenRouter support. Instead of being locked into a single LLM, you can now access 20+ models directly inside Comfy. More flexibility, less friction, same workflow. Links to the workflows below👇
0:21

ComfyUI just added OpenRouter support. Instead of being locked into a single LLM, you can now access 20+ models directly inside Comfy. More flexibility, less friction, same workflow. Links to the workflows below👇

ComfyUI

34,665 Aufrufe • vor 2 Monaten

Introducing Adjoint Sampling, a new learning algorithm that trains generative models based on scalar rewards. Based on theoretical foundations developed by FAIR, Adjoint Sampling leads to a highly scalable practical algorithm, and can become the foundation for further research into highly scalable sampling methods. Read our research paper on Adjoint Sampling and download the model, code, and benchmark ➡️
0:28

Introducing Adjoint Sampling, a new learning algorithm that trains generative models based on scalar rewards. Based on theoretical foundations developed by FAIR, Adjoint Sampling leads to a highly scalable practical algorithm, and can become the foundation for further research into highly scalable sampling methods. Read our research paper on Adjoint Sampling and download the model, code, and benchmark ➡️

AI at Meta

36,987 Aufrufe • vor 1 Jahr

ComfyUI native 3d node supports 3dgs and ply format. Integrated spark , developed by World Labs. Next we have ability to connect World labs Marble, or Tencent HunyuanWorld, or any other world model in ComfyUI. #ComfyUI
1:45

ComfyUI native 3d node supports 3dgs and ply format. Integrated spark , developed by World Labs. Next we have ability to connect World labs Marble, or Tencent HunyuanWorld, or any other world model in ComfyUI. #ComfyUI

jtydhr88

12,111 Aufrufe • vor 7 Monaten

WanVideo has been lot of fun, currently playing with applying sliding context windowing similar to AnimateDiff, the 1.3B model is especially suitable for this due to it's speed, here's 1025 frames in one go, under 5GB VRAM used, but took about 10 mins on a 5090 with 30 steps.
1:04

WanVideo has been lot of fun, currently playing with applying sliding context windowing similar to AnimateDiff, the 1.3B model is especially suitable for this due to it's speed, here's 1025 frames in one go, under 5GB VRAM used, but took about 10 mins on a 5090 with 30 steps.

Jukka Seppänen

13,808 Aufrufe • vor 1 Jahr

Birthday Story Prequel (3 min 1 sec) Made using Zeroscope and Bark. Few tech notes in the 🧵
3:01

Birthday Story Prequel (3 min 1 sec) Made using Zeroscope and Bark. Few tech notes in the 🧵

Roope Rainisto

36,018 Aufrufe • vor 2 Jahren

WAN 2.6 Reference-to-Video is available in ComfyUI! Turn 1–2 reference clips into short videos with natural motion, camera movement, and visual style!
0:29

WAN 2.6 Reference-to-Video is available in ComfyUI! Turn 1–2 reference clips into short videos with natural motion, camera movement, and visual style!

ComfyUI

42,375 Aufrufe • vor 6 Monaten

Blender+ SDXL + comfyUI = fully open source texturing workflow: 1. cameras in blender 2. render depth, edge and albedo map 3. In comfyUI use control nets to generate texture from view 5. project back and blend based on confidence (surface normal is a good indicator)
0:40

Blender+ SDXL + comfyUI = fully open source texturing workflow: 1. cameras in blender 2. render depth, edge and albedo map 3. In comfyUI use control nets to generate texture from view 5. project back and blend based on confidence (surface normal is a good indicator)

Shahriar Shahrabi | شهریار شهرابی

12,401 Aufrufe • vor 1 Jahr

I will put everything running inside ComfyUI. Blender animation control, rendering , video generation, and all in one ComfyUI.
0:50

I will put everything running inside ComfyUI. Blender animation control, rendering , video generation, and all in one ComfyUI.

jtydhr88

10,093 Aufrufe • vor 3 Monaten

Made with ComfyUI 2025 From open source to the world stage. Three years in, ComfyUI grew from an experimental playground into a production-grade creative engine, showing up in real production — film, VFX, brands, live visuals, and more. We’re marking this turning point together.
1:03

Made with ComfyUI 2025 From open source to the world stage. Three years in, ComfyUI grew from an experimental playground into a production-grade creative engine, showing up in real production — film, VFX, brands, live visuals, and more. We’re marking this turning point together.

ComfyUI

91,288 Aufrufe • vor 6 Monaten

Add suoport for using Mixamo fbx as input in ComfyUI HY Motion
0:57

Add suoport for using Mixamo fbx as input in ComfyUI HY Motion

jtydhr88

13,542 Aufrufe • vor 6 Monaten

Wan2.7 is now live as a Partner Node in ComfyUI — a comprehensive upgrade over 2.6 with better image quality, audio, motion dynamics, stylization, and consistency. More workflows. More control. Here's what's new 👇
0:21

Wan2.7 is now live as a Partner Node in ComfyUI — a comprehensive upgrade over 2.6 with better image quality, audio, motion dynamics, stylization, and consistency. More workflows. More control. Here's what's new 👇

ComfyUI

33,006 Aufrufe • vor 4 Monaten