Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

ComfyUI H3 ๐Ÿ˜ƒ Continuity Studio ComfyUI Timeline Studio Node Pack for MiniMax H3: multi-shot video, visual memory across scenes and angles, and local or cloud Story writing, on local/cloud ๐Ÿ‘‡

SD_Tutorial's profile picture

Stable Diffusion Tutorials

13,513 subscribers

21,980 Aufrufe โ€ข vor 1 Tag โ€ขvia X (Twitter)

Wissenschaft & TechnologieBildung
LIVE

Anya Rossiโ€ข Live Now

Private livecam show

10 Kommentare

Profilbild von Glenn Edwards #SoTFest2026
Glenn Edwards #SoTFest2026vor 1 Tag

Spookily, I've just created pretty much this myself over the last few days lol Using my own tooling I'm able to use H3 (or FastH3) to create long form multi-part videos (any length), with whisper driven audio, with different joins (smooth, hard cuts, new angles), memory etc

Profilbild von RAZA | AI EXPLORER
RAZA | AI EXPLORERvor 1 Tag

Multi-shot storytelling with consistent visual memory is a huge step forward for AI video creation. Great addition to ComfyUI!

Profilbild von IndyStry
IndyStryvor 1 Tag

Great tool! Thanks for sharing! Also can't believe the new test for AI detection is no longer the fingers but doors. Every AI I have seen fails drastically

Profilbild von OpenClipsAI
OpenClipsAIvor 1 Tag

This is so good! I would only change the sound of this video!

Profilbild von Not Not sure
Not Not surevor 1 Tag

Door locks glitching ruins it.

Profilbild von Ozan
Ozanvor 1 Tag

Thatโ€™s super useful, thanks!

Profilbild von Hana Ai - Marketing Network
Hana Ai - Marketing Networkvor 20 Stunden

Visual memory across scenes solves big continuity headache

Profilbild von Dinosaur Man๐Ÿฆ– ๐Ÿ‘จ
Dinosaur Man๐Ÿฆ– ๐Ÿ‘จvor 1 Tag

Holy smokes!!!!!

Profilbild von Hao
Haovor 1 Tag

Watch the timing when splitting on a guide. In an offline timeline test a 120-frame clip split at frame 60 became 73 plus 68 frames with context 39. Grid rounding added 21 frames. I have not rendered the join yet.

Profilbild von Leon Ai | tech & tools
Leon Ai | tech & toolsvor 18 Stunden

Visual memory across scenes changes everything

ร„hnliche Videos

Pruna P-H3-Image in now available in ComfyUI A distilled image model built using Minimax H3 with a 4B text encoder Run it local or on cloud โฌ‡๏ธ
0:29

Pruna P-H3-Image in now available in ComfyUI A distilled image model built using Minimax H3 with a 4B text encoder Run it local or on cloud โฌ‡๏ธ

ComfyUI

21,773 Aufrufe โ€ข vor 1 Tag

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 ๐Ÿ‘‡
0:43

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 ๐Ÿ‘‡

ComfyUI

12,740 Aufrufe โ€ข vor 2 Monaten

๐ŸŽฌ MiniMax-H3, now powered by Sol Engine in ComfyUI! Generate 5s videos with native audio on a single GPU: โšก RTX 5090: 35.5s โšก DGX Spark: 64.3s Meet Sol-H3 Studio: a visual workspace for local video generation, powered by our optimized inference engine. Open source ๐Ÿ‘‡
0:55

๐ŸŽฌ MiniMax-H3, now powered by Sol Engine in ComfyUI! Generate 5s videos with native audio on a single GPU: โšก RTX 5090: 35.5s โšก DGX Spark: 64.3s Meet Sol-H3 Studio: a visual workspace for local video generation, powered by our optimized inference engine. Open source ๐Ÿ‘‡

Enze Xie

42,601 Aufrufe โ€ข vor 19 Tagen

MiniMax-H3 R2V 5sec video extend test #comfyui
0:34

MiniMax-H3 R2V 5sec video extend test #comfyui

toyxyz

17,082 Aufrufe โ€ข vor 2 Monaten

MiniMax H3 ๐Ÿง offline prompt composer for video generation in ComfyUI. -for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. -Reuse characters, environments, voices, and keyframes across scenes. -Custom Camera Builder, visual path planners, Advanced Editing github:
0:47

MiniMax H3 ๐Ÿง offline prompt composer for video generation in ComfyUI. -for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. -Reuse characters, environments, voices, and keyframes across scenes. -Custom Camera Builder, visual path planners, Advanced Editing github:

Stable Diffusion Tutorials

18,877 Aufrufe โ€ข vor 2 Monaten

ComfyUI-Continuity One node for AI video in ComfyUI. Write a prompt, attach media with @, press Render. Support- H3, LTX-2.5, qwen img2.1, Krea2, ideogram4 -Character Tab -RefMod save -Seg & Global Seg Control -Select Continuity & Seam Optimization ๐Ÿ‘‡
0:27

ComfyUI-Continuity One node for AI video in ComfyUI. Write a prompt, attach media with @, press Render. Support- H3, LTX-2.5, qwen img2.1, Krea2, ideogram4 -Character Tab -RefMod save -Seg & Global Seg Control -Select Continuity & Seam Optimization ๐Ÿ‘‡

Stable Diffusion Tutorials

18,655 Aufrufe โ€ข vor 1 Monat

Minimax-H3 Malfoy test #malfoy #comfyui
0:31

Minimax-H3 Malfoy test #malfoy #comfyui

toyxyz

1,310,969 Aufrufe โ€ข vor 1 Monat

We're teaming up with MiniMax (official) on a community challenge built around H3. Two weeks, four ways to win an RTX 5090 or 5060 Ti, local rig or Comfy Cloud. 8/20 โ€” challenge opens 8/20โ€“9/1 โ€” build and submit 9/2 โ€” livestream with guest judges and winners Share on your socials (X, Instagram, LinkedIn, YouTube, TikTok) tagging ComfyUI MiniMax (official) #ComfyH3 so we can reshare our favorites! Click the link below to learn more ๐Ÿ‘‡
0:45

We're teaming up with MiniMax (official) on a community challenge built around H3. Two weeks, four ways to win an RTX 5090 or 5060 Ti, local rig or Comfy Cloud. 8/20 โ€” challenge opens 8/20โ€“9/1 โ€” build and submit 9/2 โ€” livestream with guest judges and winners Share on your socials (X, Instagram, LinkedIn, YouTube, TikTok) tagging ComfyUI MiniMax (official) #ComfyH3 so we can reshare our favorites! Click the link below to learn more ๐Ÿ‘‡

ComfyUI

93,177 Aufrufe โ€ข vor 2 Monaten

Minimax H3 ๐Ÿ˜ƒ VEDA Sparse Attention is now in ComfyUI -Faster video Gen -A Predictor computes the relevant subset instead of the full attention map -supports with T2VA, FL2VA and R2VA Custom node: Predictor: details in comment๐Ÿ‘‡
0:57

Minimax H3 ๐Ÿ˜ƒ VEDA Sparse Attention is now in ComfyUI -Faster video Gen -A Predictor computes the relevant subset instead of the full attention map -supports with T2VA, FL2VA and R2VA Custom node: Predictor: details in comment๐Ÿ‘‡

Stable Diffusion Tutorials

14,915 Aufrufe โ€ข vor 26 Tagen

MiniMax Design has Skills for all kinds of scenes Pick one + one line A few minutes later, itโ€™s done ComfyUI for one click local deployment SD Director for precise visual control Annual: H3 + image gen 20% off This changes the workflow
0:30

MiniMax Design has Skills for all kinds of scenes Pick one + one line A few minutes later, itโ€™s done ComfyUI for one click local deployment SD Director for precise visual control Annual: H3 + image gen 20% off This changes the workflow

Tyler Wayne

101,853 Aufrufe โ€ข vor 2 Monaten

Local, cloud, and background agents, all in a unified experience in Visual Studio Code
3:35

Local, cloud, and background agents, all in a unified experience in Visual Studio Code

Visual Studio Code

35,014 Aufrufe โ€ข vor 10 Monaten

Comfy MCP is now local and open-source! The #1 ask after Comfy Cloud MCP shipped in June. Your agent sees your actual install. So every node, custom nodes included, and every model on disk. It fetches files, starts your instance, gets a workflow to the point where it runs. It is now the easiest way to help with your local Minimax H3 workflows! Cloud MCP still does everything it did. Tell your agent where a job goes, or let it decide.
0:20

Comfy MCP is now local and open-source! The #1 ask after Comfy Cloud MCP shipped in June. Your agent sees your actual install. So every node, custom nodes included, and every model on disk. It fetches files, starts your instance, gets a workflow to the point where it runs. It is now the easiest way to help with your local Minimax H3 workflows! Cloud MCP still does everything it did. Tell your agent where a job goes, or let it decide.

ComfyUI

186,238 Aufrufe โ€ข vor 2 Monaten

Minimax-H3 black suit Malfoy test #malfoy #comfyui #Malfoid
0:29

Minimax-H3 black suit Malfoy test #malfoy #comfyui #Malfoid

toyxyz

203,599 Aufrufe โ€ข vor 1 Monat

MiniMax H3 Max is now live in ComfyUI. Post trained by fal, this model was trained for speed and precision. Can't wait for the open weights!
0:37

MiniMax H3 Max is now live in ComfyUI. Post trained by fal, this model was trained for speed and precision. Can't wait for the open weights!

ComfyUI

95,332 Aufrufe โ€ข vor 2 Monaten

Minimax-H3 little more intimate Malfoy test #malfoy #comfyui #Malfoid
0:20

Minimax-H3 little more intimate Malfoy test #malfoy #comfyui #Malfoid

toyxyz

810,877 Aufrufe โ€ข vor 1 Monat

MiniMax-H3 ๐Ÿ˜ƒ Multishot Workflow Chain multiple MiniMax-H3 shots into one continuous video with audio - in one node. Make 30 sec long video ๐Ÿ‘‡
0:30

MiniMax-H3 ๐Ÿ˜ƒ Multishot Workflow Chain multiple MiniMax-H3 shots into one continuous video with audio - in one node. Make 30 sec long video ๐Ÿ‘‡

Stable Diffusion Tutorials

24,168 Aufrufe โ€ข vor 3 Monaten

MiniMax H3 ๐Ÿ˜‰ref2vid + Blender camera motion in ComfyUI workflow + details in comment๐Ÿ‘‡
0:25

MiniMax H3 ๐Ÿ˜‰ref2vid + Blender camera motion in ComfyUI workflow + details in comment๐Ÿ‘‡

Stable Diffusion Tutorials

402,316 Aufrufe โ€ข vor 1 Monat

Made with MiniMax H3 inpainting workflow in ComfyUI, running locally on my PC.
0:31

Made with MiniMax H3 inpainting workflow in ComfyUI, running locally on my PC.

enigmatic_e

73,305 Aufrufe โ€ข vor 2 Monaten

One week left in the ComfyUI x MiniMax (official) Community Challenge. Four ways to win an RTX 5090 or RTX 5060 Ti. Fully virtual and open to everyone - local rig or Comfy Cloud. 9/1 โ€” submissions close @ 9pm PST 9/2 โ€” livestream with guest judges and winner announcements Share on your socials (X, Instagram, LinkedIn, YouTube, TikTok) tagging ComfyUI MiniMax (official) #ComfyH3 so we can reshare our favorites! Submit your video below ๐Ÿ‘‡
0:45

One week left in the ComfyUI x MiniMax (official) Community Challenge. Four ways to win an RTX 5090 or RTX 5060 Ti. Fully virtual and open to everyone - local rig or Comfy Cloud. 9/1 โ€” submissions close @ 9pm PST 9/2 โ€” livestream with guest judges and winner announcements Share on your socials (X, Instagram, LinkedIn, YouTube, TikTok) tagging ComfyUI MiniMax (official) #ComfyH3 so we can reshare our favorites! Submit your video below ๐Ÿ‘‡

ComfyUI

13,719 Aufrufe โ€ข vor 2 Monaten

Minimax H3 running locally. ~65GB of models. 12GB VRAM. RTX 4070 Ti. 100% Text-to-Video. 100% ComfyUI. Pass 1 โ†’ 960ร—544 Pass 2 โ†’ 1920ร—1088 One continuous loop built from multiple context-connected generations. No cloud. No API. CONTROL IS THE KEY. LOCAL IS THE WAY.
2:06

Minimax H3 running locally. ~65GB of models. 12GB VRAM. RTX 4070 Ti. 100% Text-to-Video. 100% ComfyUI. Pass 1 โ†’ 960ร—544 Pass 2 โ†’ 1920ร—1088 One continuous loop built from multiple context-connected generations. No cloud. No API. CONTROL IS THE KEY. LOCAL IS THE WAY.

Maurice Bourdon

237,581 Aufrufe โ€ข vor 2 Monaten