正在加载视频...

视频加载失败

返回首页

Tencent HY-Motion in ComfyUI. WIiP, will push code soon.

jtydhr88's profile picture

jtydhr88

3,380 subscribers

71,245 次观看 • 10 个月前 •via X (Twitter)

科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

16 条评论

Purz.ai 的头像
Purz.ai10 个月前

YESSSSS you work so fast

Observer 的头像
Observer10 个月前

Is there a convenient way to hook this into a video diffusion / wan2.2 workflow to get consistent animations?

Stefan Vaskevich 的头像
Stefan Vaskevich10 个月前

sir, how did you manage to install fbxsdkpy in new ComfyUI, it seems it has problems with python 3.13? would really appreaciate an advice

Agentsfy 的头像
Agentsfy10 个月前

Thank You

Himanshu Kumar 的头像
Himanshu Kumar10 个月前

jtydhr88 observed Tencent HY-Motion integration within ComfyUI.

MinusGix 的头像
MinusGix10 个月前

I wonder why they went with Qwen 8b rather than a smaller model given lack of complex prompting, whether it gave substantially better generalization across different actions or what, huh

Gawin Chen 的头像
Gawin Chen9 个月前

that's so cool

Alexis ROLLAND 的头像
Alexis ROLLAND10 个月前

Looking forward to it!

ごるごしべりあ / 原神なりきりVTuber 的头像
ごるごしべりあ / 原神なりきりVTuber10 个月前

感謝感激雨霰

Karan Jagtiani 的头像
Karan Jagtiani10 个月前

Looks solid. Any plans for documentation or examples to help with the integration?

Jay Sensei👾 的头像
Jay Sensei👾10 个月前

🤗

Linjax 的头像
Linjax10 个月前

Merci d’avoir partagé sur votre github

MXSHOOT 的头像
MXSHOOT10 个月前

need tutorial :3

Enid Pinxit 的头像
Enid Pinxit10 个月前

🔥🔥🔥

𝕭𝖎𝖙𝖔𝖚 的头像
𝕭𝖎𝖙𝖔𝖚10 个月前

What’s the music is it?

Hector 的头像
Hector10 个月前

can this work on game engine skeletons, ie UE5 manny or metahumans?

相关视频

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 次观看 • 10 个月前

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 次观看 • 10 个月前

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

10,358 次观看 • 7 个月前

Tested with TripoSplat in ComfyUI
0:52

Tested with TripoSplat in ComfyUI

jtydhr88

17,086 次观看 • 5 个月前

HY 3D advanced features are now available in ComfyUI. This update brings production-ready 3D post-processing from Tencent Hy, which is closer to the same workflow. - 3D Parts Decomposition: split assets into editable components - UV Unwrapping: prepare models for texturing faster - Smart Topology: generate cleaner, production-friendly meshes
0:28

HY 3D advanced features are now available in ComfyUI. This update brings production-ready 3D post-processing from Tencent Hy, which is closer to the same workflow. - 3D Parts Decomposition: split assets into editable components - UV Unwrapping: prepare models for texturing faster - Smart Topology: generate cleaner, production-friendly meshes

ComfyUI

59,035 次观看 • 8 个月前

ComfyTV, the infinite canvas-based app that truly belongs to ComfyUI 1. Seamlessly integrates with the full ComfyUI ecosystem — subgraphs, plugins, everything 2. Bring-your-own workflows, drop in any workflow from your existing ComfyUI 3. Each step's output auto-propagates downstream 4. Live result updates 5. Native ComfyUI canvas 6. 100% local generation, no external APIs 7. Zero extra Python dependencies
1:41

ComfyTV, the infinite canvas-based app that truly belongs to ComfyUI 1. Seamlessly integrates with the full ComfyUI ecosystem — subgraphs, plugins, everything 2. Bring-your-own workflows, drop in any workflow from your existing ComfyUI 3. Each step's output auto-propagates downstream 4. Live result updates 5. Native ComfyUI canvas 6. 100% local generation, no external APIs 7. Zero extra Python dependencies

jtydhr88

21,744 次观看 • 4 个月前

ComfyUI supports Qwen Image layered on day0, it is cool, then…we need some real layers management to control them, try my previous custom plugin ComfyUI-PolotnoCanvasEditor #ComfyUI
0:38

ComfyUI supports Qwen Image layered on day0, it is cool, then…we need some real layers management to control them, try my previous custom plugin ComfyUI-PolotnoCanvasEditor #ComfyUI

jtydhr88

82,321 次观看 • 10 个月前

ComfyUI 3D Node Improvements 03/18 (Multi-layer Output) Recently, I've made several changes and improvements to Load3D: 1. Support for simultaneous output of multiple layers - original, mask, normal maps, lineart 2. Performance improvements - rendering only occurs when the mouse is over the node 3. UI changes - using menus to manage the buttons in the top left corner 4. UI changes - temporarily removed depth mode from material options 5. Many backend code changes. #ComfyUI
1:03

ComfyUI 3D Node Improvements 03/18 (Multi-layer Output) Recently, I've made several changes and improvements to Load3D: 1. Support for simultaneous output of multiple layers - original, mask, normal maps, lineart 2. Performance improvements - rendering only occurs when the mouse is over the node 3. UI changes - using menus to manage the buttons in the top left corner 4. UI changes - temporarily removed depth mode from material options 5. Many backend code changes. #ComfyUI

jtydhr88

17,581 次观看 • 1 年前

WIP, ComfyUI native node — painter node
1:17

WIP, ComfyUI native node — painter node

jtydhr88

21,106 次观看 • 8 个月前

Just something for Christmas fun! Convert ComfyUI into 3D space! It might not have any practical purpose — I know there are plenty of cool commercial products out there. But isn’t this exactly what makes ComfyUI, as an open-source project, so fun? As long as it’s enjoyable, isn’t that enough? Long live fun, and open source will win!
0:53

Just something for Christmas fun! Convert ComfyUI into 3D space! It might not have any practical purpose — I know there are plenty of cool commercial products out there. But isn’t this exactly what makes ComfyUI, as an open-source project, so fun? As long as it’s enjoyable, isn’t that enough? Long live fun, and open source will win!

jtydhr88

11,654 次观看 • 10 个月前

Blender, but running inside browser. Next, move it into ComfyUI.
0:52

Blender, but running inside browser. Next, move it into ComfyUI.

jtydhr88

35,491 次观看 • 7 个月前

ComfyUI-Mesh2Motion 1.2.0 Custom FBX import is now built into ComfyUI-Mesh2Motion. Load any FBX 3D animation, combine it with professional camera presets, and take precise control over your AI video output.
0:41

ComfyUI-Mesh2Motion 1.2.0 Custom FBX import is now built into ComfyUI-Mesh2Motion. Load any FBX 3D animation, combine it with professional camera presets, and take precise control over your AI video output.

jtydhr88

13,972 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

79,983 次观看 • 7 个月前

Let’s use Minimax H3 in ComfyUI in a more elegant way. Video tutorial for ComfyTV:@ image references and a dynamic number of image inputs, then videos edit & FX
6:07

Let’s use Minimax H3 in ComfyUI in a more elegant way. Video tutorial for ComfyTV:@ image references and a dynamic number of image inputs, then videos edit & FX

jtydhr88

14,680 次观看 • 3 个月前

Add Camera view for ComfyUI Qwen Multiple angles 3D camera node
0:30

Add Camera view for ComfyUI Qwen Multiple angles 3D camera node

jtydhr88

19,629 次观看 • 9 个月前

Did you try Tencent HY World model on fal?
0:20

Did you try Tencent HY World model on fal?

Aykut

14,373 次观看 • 1 年前

🚀 Just released a LoRA for Wan 2.1 that adds realistic drone-style push-in motion. Model: Wan 2.1 I2V - 14B 720p Trained on 100 clips — and refined over 40+ versions. Trigger: Push-in_camera 🎥 + ComfyUI workflow included for easy use Perfect if you want your videos to actually *move*. 👉 #AI #LoRA #wan21 #generativevideo ComfyUI Made in collaboration with Kartel.ai
0:23

🚀 Just released a LoRA for Wan 2.1 that adds realistic drone-style push-in motion. Model: Wan 2.1 I2V - 14B 720p Trained on 100 clips — and refined over 40+ versions. Trigger: Push-in_camera 🎥 + ComfyUI workflow included for easy use Perfect if you want your videos to actually *move*. 👉 #AI #LoRA #wan21 #generativevideo ComfyUI Made in collaboration with Kartel.ai

Lovis Odin

22,869 次观看 • 1 年前

MiniMax H3 😉ref2vid + Blender camera motion in ComfyUI workflow + details in comment👇
0:25

MiniMax H3 😉ref2vid + Blender camera motion in ComfyUI workflow + details in comment👇

Stable Diffusion Tutorials

402,316 次观看 • 1 个月前

A true Blender running inside ComfyUI. Viewport preview, rendering — not sure how far this’ll go, but I’ll take it one step at a time.
0:53

A true Blender running inside ComfyUI. Viewport preview, rendering — not sure how far this’ll go, but I’ll take it one step at a time.

jtydhr88

31,009 次观看 • 7 个月前

Opus 5.5, Beethoven, and Fate. Inspired by "I'm Upping My P(doom)", a five-minute classical music video, written as code and rendered frame by frame by Claude (Opus 5.5) in Claude Code. It draws on seven classical works. No image or video generation model was used anywhere in the film. The source code is open:
5:06

Opus 5.5, Beethoven, and Fate. Inspired by "I'm Upping My P(doom)", a five-minute classical music video, written as code and rendered frame by frame by Claude (Opus 5.5) in Claude Code. It draws on seven classical works. No image or video generation model was used anywhere in the film. The source code is open:

jtydhr88

24,980 次观看 • 1 个月前