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.

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

vadim epstein

2,294 subscribers

62,237 views • 2 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 Comments

vadim epstein2 years ago

one more, with dramatic edits

Retropunk2 years ago

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

Infinite Vibes2 years ago

Infinite Zeroscope!? Wonderful, thank you.

vadim epstein2 years ago

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

Nathan Shipley2 years ago

Awesome, Vadim 🙌

vadim epstein2 years ago

thank you sir

Andrey Flat2 years ago

oooooooooooooooooooffffffffff

Orb2 years ago

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

Krzysztof Gonia2 years ago

Good enough to be used in music videos. Nice.

Related Videos

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

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 views • 2 years ago

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

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

18,159 views • 1 year ago

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!🧵

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 views • 2 years ago

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]

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

182,476 views • 2 years ago

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-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 views • 1 year ago

ComfyUI, even on vacation. 🌴 While on vacation, enigmatic_e left the laptop behind. A phone and an AI agent connected to ComfyUI MCP were all it took to run ComfyUI workflows through natural conversation while vacation continued. To try this workflow and learn more about ComfyUI MCP, check out the links below 👇

ComfyUI, even on vacation. 🌴 While on vacation, enigmatic_e left the laptop behind. A phone and an AI agent connected to ComfyUI MCP were all it took to run ComfyUI workflows through natural conversation while vacation continued. To try this workflow and learn more about ComfyUI MCP, check out the links below 👇

ComfyUI

123,971 views • 2 months ago

FastH3 by FastVideo is now available in ComfyUI Video and native stereo audio, generated together, in seconds. Best for: → Previz and animatics that need lots of takes, quickly → Timing and dialogue tests before committing to a full-quality render → Short-form and social work on tight turnarounds Run it locally in ComfyUI and soon on Cloud ⬇️

FastH3 by FastVideo is now available in ComfyUI Video and native stereo audio, generated together, in seconds. Best for: → Previz and animatics that need lots of takes, quickly → Timing and dialogue tests before committing to a full-quality render → Short-form and social work on tight turnarounds Run it locally in ComfyUI and soon on Cloud ⬇️

ComfyUI

47,335 views • 21 days ago

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.

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 views • 10 months ago

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 👇

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 views • 3 years ago

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 👇

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 views • 2 months ago

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

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 🔶

30,919 views • 8 months ago

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

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

Roope Rainisto

36,029 views • 3 years ago

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 ➡️

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 views • 1 year ago

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.

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

14,778 views • 1 year ago

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 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

35,146 views • 4 months ago

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

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 views • 9 months ago

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!

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 views • 8 months ago

heres what ive been working on !!!!!! - vastly improved collisions - party members catch up to you after unfollowing and then following you, instead of teleporting - implemented sliding - added the dust effect to climbing #deltaruneㅤㅤㅤ

heres what ive been working on !!!!!! - vastly improved collisions - party members catch up to you after unfollowing and then following you, instead of teleporting - implemented sliding - added the dust effect to climbing #deltaruneㅤㅤㅤ

borty

48,479 views • 2 months ago