Loading video...

Video Failed to Load

Go Home

Wan2.1-VACE 14B & 1.3B are now natively supported in ComfyUI! This model from Wan brings all-in-one editing capability to your video generation: 🔹Text-to-Video & Image-to-Video 🔹 Video-to-video (Pose & depth control) 🔹 Inpainting & Outpainting 🔹 Character + object reference

ComfyUI's profile picture

ComfyUI

47,229 subscribers

21,517 views • 1 year ago •via X (Twitter)

ArtsScience & TechnologyEducation
LIVE

Anya Rossi• Live Now

Private livecam show

8 Comments

ComfyUI's profile picture
ComfyUI1 year ago

To get started, update to the latest version and go to: Workflow → Template → Wan2.1-VACE, or download the workflows in the blog. Check the Video-to-Video Pose Control workflow below:

ComfyUI's profile picture
ComfyUI1 year ago

Video-to-Video Depth Control Example:

ComfyUI's profile picture
ComfyUI1 year ago

Check our blog and documentation for more workflows: Blog: Documentation: Content: @ComfyUIWiki @Yo9oTatara Music: @jojodecayz

UserInterface's profile picture
UserInterface4 years ago

Stay up to date on the latest Music, News, Reviews and ways to improve your Lifestyle. Create a channel & invite your friends. #music #movies #food #games #fashion

JQ's profile picture
JQ1 year ago

@Alibaba_Wan Nice!!!… Any chance of sliding context window support?

huwhitememes ✦ MKS's profile picture
huwhitememes ✦ MKS1 year ago

@Alibaba_Wan

Єl Lіисэ De Los Nadies's profile picture
Єl Lіисэ De Los Nadies1 year ago

@Alibaba_Wan Is the song available?

Hrmkmdtv's profile picture
Hrmkmdtv1 year ago

@Alibaba_Wan comfy updates are always delights

Related Videos

Marey Realism 1.5 by Moonvalley is now live in ComfyUI API nodes! First video model trained only on 100% licensed 1080P footages — pro quality, production-ready, and commercially safe. Now available: 🔹 Text-to-Video 🔹 Image-to-Video 🕙 Pose and Motion Transfer nodes coming soon 🧵👇
0:48

Marey Realism 1.5 by Moonvalley is now live in ComfyUI API nodes! First video model trained only on 100% licensed 1080P footages — pro quality, production-ready, and commercially safe. Now available: 🔹 Text-to-Video 🔹 Image-to-Video 🕙 Pose and Motion Transfer nodes coming soon 🧵👇

ComfyUI

14,606 views • 1 year ago

Wan2.2-S2V is now natively supported in ComfyUI! Transform static images and audio into cinematic-quality videos with synchronized lip-sync and natural movements. 🔹 Audio-driven video generation 🔹 Cinematic-grade quality output 🔹 Minute-level long-form videos 🔹 Multi-format support (full/half-body) 🔹 Enhanced motion control via text 🧵👇
0:46

Wan2.2-S2V is now natively supported in ComfyUI! Transform static images and audio into cinematic-quality videos with synchronized lip-sync and natural movements. 🔹 Audio-driven video generation 🔹 Cinematic-grade quality output 🔹 Minute-level long-form videos 🔹 Multi-format support (full/half-body) 🔹 Enhanced motion control via text 🧵👇

ComfyUI

49,251 views • 10 months ago

✨ All in One, Wan for All✨ We are excited to introduce our latest model to our talented community creators: Wan2.1-VACE, All-in-One Video Creation and Editing model. Model size: 1.3B, 14B License: Apache-2.0 📌 Wan2.1-VACE provides solutions for various tasks, including reference-to-video generation (R2V), video-to-video editing (V2V), and masked video-to-video editing (MV2V), allowing creators to freely combine these capabilities to achieve complex tasks. 👉 Multimodal inputs enhancing the controllability of video generation. 👉 Unified single model for consistent solutions across tasks. 👉 Free combination of capabilities unlocking deeper creative potentials. 😄 Wanna try? 1️⃣ Github: 2️⃣Hugging Face: 3️⃣ ModelScope: 4️⃣ API Service: 5️⃣ Coming soon!
1:06

✨ All in One, Wan for All✨ We are excited to introduce our latest model to our talented community creators: Wan2.1-VACE, All-in-One Video Creation and Editing model. Model size: 1.3B, 14B License: Apache-2.0 📌 Wan2.1-VACE provides solutions for various tasks, including reference-to-video generation (R2V), video-to-video editing (V2V), and masked video-to-video editing (MV2V), allowing creators to freely combine these capabilities to achieve complex tasks. 👉 Multimodal inputs enhancing the controllability of video generation. 👉 Unified single model for consistent solutions across tasks. 👉 Free combination of capabilities unlocking deeper creative potentials. 😄 Wanna try? 1️⃣ Github: 2️⃣Hugging Face: 3️⃣ ModelScope: 4️⃣ API Service: 5️⃣ Coming soon!

Wan

198,528 views • 1 year ago

🎉 ComfyUI now natively supports NVIDIA’s Cosmos-Predict2 model family! Cosmos-Predict2 brings high-fidelity, physics-aware Image generation and Video2World (Image-to-Video) generation. Another reality inside ComfyUI!
0:41

🎉 ComfyUI now natively supports NVIDIA’s Cosmos-Predict2 model family! Cosmos-Predict2 brings high-fidelity, physics-aware Image generation and Video2World (Image-to-Video) generation. Another reality inside ComfyUI!

ComfyUI

16,925 views • 1 year ago

#StarAI has landed on Base 🟦 🎬 Unleash your creativity with our tools: 🔹 Text-to-Video 🔹 Image-to-Video 🔹 Frame-to-Video 🔹 Stitching 🎁 Big community contests & trading rewards are in the works. Try it now, and get ready for what’s next ✨ 👉 Learn more: #aivideos #Base #Web3AI
0:22

#StarAI has landed on Base 🟦 🎬 Unleash your creativity with our tools: 🔹 Text-to-Video 🔹 Image-to-Video 🔹 Frame-to-Video 🔹 Stitching 🎁 Big community contests & trading rewards are in the works. Try it now, and get ready for what’s next ✨ 👉 Learn more: #aivideos #Base #Web3AI

StarAI

32,140 views • 9 months ago

Wan2.2 is now natively supported in ComfyUI on Day 0! 🔹 A next-gen video model with MoE (Mixture of Experts) architecture with dual noise experts, under Apache 2.0 license! - Cinematic-level Aesthetic Control - Large-scale Complex Motion - Precise Semantic Compliance 📚 Versions available: - Wan2.2-TI2V-5B: FP16 - Wan2.2-I2V-14B: FP16/FP8 - Wan2.2-T2V-14B: FP16/FP8 💻 Down to 8GB VRAM requirement for the 5B version with ComfyUI auto-offloading.
0:55

Wan2.2 is now natively supported in ComfyUI on Day 0! 🔹 A next-gen video model with MoE (Mixture of Experts) architecture with dual noise experts, under Apache 2.0 license! - Cinematic-level Aesthetic Control - Large-scale Complex Motion - Precise Semantic Compliance 📚 Versions available: - Wan2.2-TI2V-5B: FP16 - Wan2.2-I2V-14B: FP16/FP8 - Wan2.2-T2V-14B: FP16/FP8 💻 Down to 8GB VRAM requirement for the 5B version with ComfyUI auto-offloading.

ComfyUI

84,423 views • 11 months ago

Seedream 5.0 Pro is now in ComfyUI via Partner Nodes. ByteDance's latest image model brings: → Character & product consistency across edits → Precision region editing → Infographics, flowcharts & structured layouts → In-image text across 14 languages One model. Text-to-image, editing, and multi-image inputs. Click the link below for the workflow 👇
0:32

Seedream 5.0 Pro is now in ComfyUI via Partner Nodes. ByteDance's latest image model brings: → Character & product consistency across edits → Precision region editing → Infographics, flowcharts & structured layouts → In-image text across 14 languages One model. Text-to-image, editing, and multi-image inputs. Click the link below for the workflow 👇

ComfyUI

14,756 views • 5 days ago

Smart AI assistant for your ComfyUI workflow! Introducing ComfyUI-Copilot V2 - a powerful custom node by Pixelle AI that allows you to talk to your workflows! 🔹 Create and edit custom workflows from your descriptions 🔹 Smart debugging: detect and fix workflow errors 🔹 Custom node and model recommendation + explanation 🔹 Enhanced AI agent: provide advice based on your local ComfyUI setup Perfect for users who want to automate their workflow creation and management!
1:35

Smart AI assistant for your ComfyUI workflow! Introducing ComfyUI-Copilot V2 - a powerful custom node by Pixelle AI that allows you to talk to your workflows! 🔹 Create and edit custom workflows from your descriptions 🔹 Smart debugging: detect and fix workflow errors 🔹 Custom node and model recommendation + explanation 🔹 Enhanced AI agent: provide advice based on your local ComfyUI setup Perfect for users who want to automate their workflow creation and management!

ComfyUI

26,259 views • 10 months ago

Incredible Bullet Time re-creation — by Corridor All you need: 1 PC, phone cameras, and ComfyUI. Wan 2.1 + VACE workflow with multi-control videos for z-depth, pose & camera motion. Workflow + Full Video 👇
1:13

Incredible Bullet Time re-creation — by Corridor All you need: 1 PC, phone cameras, and ComfyUI. Wan 2.1 + VACE workflow with multi-control videos for z-depth, pose & camera motion. Workflow + Full Video 👇

ComfyUI

19,031 views • 9 months ago

🗞️ Ava's Frid-AI Roundup! Welcome to Solidus Ai Tech Friday Roundup! 🔹 YouTube to Stop Paying for Cheap AI Videos 🔹 xAI Debuts Grok 4 With New SuperGrok Subscription 🔹 Google Adds Image‑to‑Video Magic to Veo 3 🔹 Perplexity Launches Comet, an AI‑Native Browser 🔹 Meta Pays $200M to Snag an AI Star From Apple 🔹 Isomorphic Labs Nears Human Trials of AI‑Designed Drugs 🔹 Moonvalley Releases Marey, an ‘Ethical’ AI Video Model
2:30

🗞️ Ava's Frid-AI Roundup! Welcome to Solidus Ai Tech Friday Roundup! 🔹 YouTube to Stop Paying for Cheap AI Videos 🔹 xAI Debuts Grok 4 With New SuperGrok Subscription 🔹 Google Adds Image‑to‑Video Magic to Veo 3 🔹 Perplexity Launches Comet, an AI‑Native Browser 🔹 Meta Pays $200M to Snag an AI Star From Apple 🔹 Isomorphic Labs Nears Human Trials of AI‑Designed Drugs 🔹 Moonvalley Releases Marey, an ‘Ethical’ AI Video Model

AITECH CLOUD NETWORK

47,555 views • 1 year ago

🗞️ Ava's Frid-AI Roundup! Welcome to Solidus Ai Tech Friday Roundup! 🔹 Mistral Agents API with Web Search and Image Generation 🔹 Rodrigo Liang at Web Summit Vancouver 🔹 Claude Adds Voice Control 🔹 Google Launches SignGemma for Sign Language Translation 🔹 Factory AI Debuts Droids for Dev Workflows 🔹 Perplexity Labs for Automated Report/App Generation 🔹 FLUX.1 Kontext Text-Based Image Editing
1:54

🗞️ Ava's Frid-AI Roundup! Welcome to Solidus Ai Tech Friday Roundup! 🔹 Mistral Agents API with Web Search and Image Generation 🔹 Rodrigo Liang at Web Summit Vancouver 🔹 Claude Adds Voice Control 🔹 Google Launches SignGemma for Sign Language Translation 🔹 Factory AI Debuts Droids for Dev Workflows 🔹 Perplexity Labs for Automated Report/App Generation 🔹 FLUX.1 Kontext Text-Based Image Editing

AITECH

36,645 views • 1 year ago

ComfyUI 0.3.51: Our biggest frontend update since June ✨ What’s new: 🔹 Subgraph officially in stable releases 🔹 The new Manager UI 🔹 Mini Map navigation 🔹 Tab previews + Shortcut panel 🔹 Standard navigation mode 🔹 Help Center with changelogs
2:01

ComfyUI 0.3.51: Our biggest frontend update since June ✨ What’s new: 🔹 Subgraph officially in stable releases 🔹 The new Manager UI 🔹 Mini Map navigation 🔹 Tab previews + Shortcut panel 🔹 Standard navigation mode 🔹 Help Center with changelogs

ComfyUI

15,234 views • 10 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!
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 views • 5 months ago

🚀 Exciting News! 🚀 Check out our latest video summarizing our life-time earning opportunity Airdrop! 🎥✨ 🔹 What is CryptoPixels? 🔹 How we pay you? 🔹 Why we are offering this passive income airdrop? 🔹 How much you can earn from this airdrop? 🔹 How to participate in the airdrop? 🔹 Why not to miss it? Don’t miss out on this lifetime income opportunity! Watch the video now and join the CryptoPixels community. 🌐💸
3:01

🚀 Exciting News! 🚀 Check out our latest video summarizing our life-time earning opportunity Airdrop! 🎥✨ 🔹 What is CryptoPixels? 🔹 How we pay you? 🔹 Why we are offering this passive income airdrop? 🔹 How much you can earn from this airdrop? 🔹 How to participate in the airdrop? 🔹 Why not to miss it? Don’t miss out on this lifetime income opportunity! Watch the video now and join the CryptoPixels community. 🌐💸

CPixels

17,031 views • 2 years ago

A rare LEGENDARY Crimson Horse to match your LEGENDARY status in Crimson Desert! Tips to tame: 🔹Switch to high FPS mode 🔹Stamina 300+ 🔹While taming go for top view angle (as shown in the video) Location and how to find the horse is in the video.
0:23

A rare LEGENDARY Crimson Horse to match your LEGENDARY status in Crimson Desert! Tips to tame: 🔹Switch to high FPS mode 🔹Stamina 300+ 🔹While taming go for top view angle (as shown in the video) Location and how to find the horse is in the video.

SpawnYaard 🎮

82,857 views • 2 months ago

Grok Imagine API just released A world-class video generation + video editing model Text-to-Video: Turn simple prompts into rich video clips with audio Image Generation + Editing: Bring ideas to life with visuals from scratch Video Editing Tools: Restyle scenes, add/remove props, control motion Best-in-Class Quality + Low Latency: Designed to deliver fast, cost-efficient results API pricing: Image input: $0.002 Video input : $0.01 Video output : $0.05
0:22

Grok Imagine API just released A world-class video generation + video editing model Text-to-Video: Turn simple prompts into rich video clips with audio Image Generation + Editing: Bring ideas to life with visuals from scratch Video Editing Tools: Restyle scenes, add/remove props, control motion Best-in-Class Quality + Low Latency: Designed to deliver fast, cost-efficient results API pricing: Image input: $0.002 Video input : $0.01 Video output : $0.05

X Freeze

15,078 views • 5 months ago

Ever wondered how to yield farm on Cardano and earn 40–50% APR? In this video I break down: 🔹how it works 🔹which pools to choose 🔹how to maximise your rewards without getting rekt👇
9:11

Ever wondered how to yield farm on Cardano and earn 40–50% APR? In this video I break down: 🔹how it works 🔹which pools to choose 🔹how to maximise your rewards without getting rekt👇

Linda

23,915 views • 8 months ago

AI Video tool showdown!🎬 Five of the best AI video tools go head-to-head! I tried 3 attempts with each of them 🔹Kling 2.0 🔹Gen-4 Turbo 🔹Luma Ray2 🔹Veo2 🔹Hailuo Which one do you think is the best? Let me know in the comments
0:25

AI Video tool showdown!🎬 Five of the best AI video tools go head-to-head! I tried 3 attempts with each of them 🔹Kling 2.0 🔹Gen-4 Turbo 🔹Luma Ray2 🔹Veo2 🔹Hailuo Which one do you think is the best? Let me know in the comments

MayorkingAI

26,686 views • 1 year ago

Grok Imagine is now LIVE in Hedra DAY 0 ! 🚀 Stunning photorealistic images & videos. Lightning-fast generation Easy edits for elements, styles & more Text to Image. Image Editing. Text to Video. Image to Video All inside Hedra. Try it now.
0:32

Grok Imagine is now LIVE in Hedra DAY 0 ! 🚀 Stunning photorealistic images & videos. Lightning-fast generation Easy edits for elements, styles & more Text to Image. Image Editing. Text to Video. Image to Video All inside Hedra. Try it now.

Hedra

749,171 views • 5 months ago