Patreon
Home / Videos / Make Any Image Sing or Talk: 45-Second Lip Sync Videos With

Make Any Image Sing or Talk: 45-Second Lip Sync Videos With LTX 2 Audio to Video (ComfyUI)

ComfyUI auto installer that sets up Sage Attention, Triton, xFormers and Flash Attention in one click, with ready presets for image, video and lip sync models.

Published Jan 30, 2026 · 7,046 views · Watch on YouTube

Get the app and files

ComfyUI Auto Installer: 1-Click Windows, Linux & Cloud With Presets

ComfyUI Auto Installer: 1-Click Windows, Linux & Cloud With Presets

ComfyUI auto installer that sets up Sage Attention, Triton, xFormers and Flash Attention in one click, with ready presets for image, video and lip sync models.

LTX 2 Ultimate Tutorial: ComfyUI & SwarmUI on Windows and Cloud

LTX 2 Ultimate Tutorial: ComfyUI & SwarmUI on Windows and Cloud

LTX2 video tutorial covering ComfyUI and SwarmUI setup, model downloads and ready presets plus Z-Image Base, on GPUs with as low as 6 GB VRAM.

Chapters

  1. 0:00 Intro: ComfyUI + SwarmUI presets, Z-Image, model downloader, cloud installs
  2. 0:28 Free prompt enhancement with Google AI Studio (prepared prompt file)
  3. 1:26 Demo: 45s audio-driven lip-sync image→video (LTX 2)
  4. 2:25 Quick demos: ComfyUI image→video, text→video, Z-Image base
  5. 3:43 Quick demos: SwarmUI LTX 2 image→video + Z-Image base
  6. 4:46 Install/update presets zip (v78+): extract & overwrite everything
  7. 5:11 Upgrade to CUDA 13 safely: delete venv then run ComfyUI update/install
  8. 6:00 Windows prereqs + the always-updated setup guide referenced in description
  9. 6:42 Install required node bundles: (1) SwarmUI extra nodes + (100) LTX audio
  10. 7:29 VRAM-optimized launcher: no-VRAM / cache / smart-memory / precision choices
  11. 9:36 Share one model library: configure extra_model_paths.yaml (no duplicates)
  12. 10:25 Model Downloader overview: set base path + one-click bundles for SwarmUI/ComfyUI
  13. 11:43 Download LTX 2 core bundle: multi-connection download + merge + hash verify
  14. 12:12 Low-VRAM path: GGUF distilled models vs recommended FP8-scaled defaults
  15. 14:16 URL Downloader: Civitai/HF links, folder targeting, and optional API keys
  16. 14:54 ComfyUI preset pack tour: LTX2 (I2V/T2V/audio) + Z-Image (base/2× upscale)
  17. 15:16 ComfyUI audio lip-sync preset: image + resolution + audio setup
  18. 16:58 Frames & prompting: 24fps math, run/stop frame count, lyrics/subtitles prompts
  19. 17:59 Quality/perf knobs: CRF, VRAM monitoring, and low-VRAM args recap
  20. 20:22 Review result + move to LTX 2 image→video preset workflow
  21. 21:50 Prompt enhancer workflow: drag prompt file into AI Studio (optionally add image)
  22. 24:11 Z-Image troubleshooting: disable Sage Attention and restart
  23. 24:32 Z-Image base + 2× upscale preset: when to use it and what to expect
  24. 26:47 Outputs & reproducibility: where renders save + drag PNG to reload metadata
  25. 27:57 Update SwarmUI via zip: get latest presets + utilities
  26. 28:27 SwarmUI setup: ComfyUI backend, passing args, and pointing to model folders
  27. 30:21 SwarmUI image→video: direct apply + init image workflow
  28. 31:17 Fix model load/caching issues: add --use-cache-none when needed
  29. 32:51 SwarmUI text→video + upscale: duration/frames, half-res then upscale rules
  30. 33:52 SwarmUI outputs: output_local/raw + metadata saved with generations
  31. 35:05 SwarmUI Z-Image: base vs 2× upscale comparison + speed notes
  32. 36:58 Image comparison slider tool: quick before/after inspection
  33. 37:51 RunPod start: template choice, CUDA/driver constraints, optional storage volume
  34. 43:30 RunPod Jupyter: upload ComfyUI zip, extract, install bundles (1+100)
  35. 46:28 RunPod: run Model Downloader, start ComfyUI, connect via exposed port
  36. 52:05 RunPod: switch to SwarmUI, map folders (case-sensitive), import presets
  37. 55:43 RunPod: download outputs as archive + stop vs terminate cost control
  38. 57:55 SimplePod: cheaper/faster alternative + persistent volume setup highlights
  39. 63:52 Massed Compute: deploy with coupon + connect via ThinLinc (shared folder setup)
  40. 68:17 Massed Compute: install bundles + download models (disk speed advantage)
  41. 70:48 Massed Compute: start ComfyUI, connect from PC, run lip-sync preset
  42. 74:26 Massed Compute: hook SwarmUI to ComfyUI backend + text→video demo
  43. 77:02 Wrap-up: recap providers + next steps

About this video

LTX 2 is the newest state of the art (SOTA) Open Source video generation model and tutorial will show you how to use it with very best and most performant way in ComfyUI and also in SwarmUI. Moreover, Z Image Base model published and I will show how to use Z Image Base with most amazing preset and workflow as well. Furthermore, this tutorial will show you how to install, update, setup, download ComfyUI and SwarmUI and models and presets and workflows both on Windows and on RunPod, Massed Compute and SimplePod. Linux users can use Massed Compute scripts and installers directly. This is a masterpiece entire lecture level complete tutorial. This video will kickstart your AI journey 100x. Both local Windows and Cloud.

📂 Resources & Links:

🤖 ComfyUI Installer and Presets Zip File With CUDA 13: [ https://www.patreon.com/posts/ComfyUI-Installers-105023709 ]

💻 SwarmUI Installer and Presets Zip File: [ https://www.patreon.com/posts/SwarmUI-Install-Presets-114517862 ]

🚀 Model Downloader Zip File: [ https://www.patreon.com/posts/Model-Downloader-114517862 ]

🚆 SECourses Musubi Trainer (Model Quantize and Train App): [ https://www.patreon.com/posts/SECourses-Musubi-Trainer-137551634 ]

🛠️ Image Comparison Slider Tool: [ https://www.patreon.com/posts/image-video-comparison-slider-app-133935178 ]

👋 SECourses Discord Channel for 7/24 Support: [ https://bit.ly/SECoursesDiscord ]

ℹ️ SimplePod Register : https://simplepod.ai/ref?user=secourses

ℹ️ SimplePod Template : https://dash.simplepod.ai/account/explore/100/ref-secourses/

ℹ️ RunPod Register : https://get.runpod.io/955rkuppqv4h

ℹ️ RunPod Template : https://get.runpod.io/SECourses_CU13

ℹ️ Massed Compute Register : https://bit.ly/SECoursesMassedCompute

⏱️ TIMESTAMPS

0:00 Intro: ComfyUI + SwarmUI presets, Z-Image, model downloader, cloud installs

0:28 Free prompt enhancement with Google AI Studio (prepared prompt file)

1:26 Demo: 45s audio-driven lip-sync image→video (LTX 2)

2:25 Quick demos: ComfyUI image→video, text→video, Z-Image base

3:43 Quick demos: SwarmUI LTX 2 image→video + Z-Image base

4:46 Install/update presets zip (v78+): extract & overwrite everything

5:11 Upgrade to CUDA 13 safely: delete venv then run ComfyUI update/install

6:00 Windows prereqs + the always-updated setup guide referenced in description

6:42 Install required node bundles: (1) SwarmUI extra nodes + (100) LTX audio

7:29 VRAM-optimized launcher: no-VRAM / cache / smart-memory / precision choices

9:36 Share one model library: configure extra_model_paths.yaml (no duplicates)

10:25 Model Downloader overview: set base path + one-click bundles for SwarmUI/ComfyUI

11:43 Download LTX 2 core bundle: multi-connection download + merge + hash verify

12:12 Low-VRAM path: GGUF distilled models vs recommended FP8-scaled defaults

14:16 URL Downloader: Civitai/HF links, folder targeting, and optional API keys

14:54 ComfyUI preset pack tour: LTX2 (I2V/T2V/audio) + Z-Image (base/2× upscale)

15:16 ComfyUI audio lip-sync preset: image + resolution + audio setup

16:58 Frames & prompting: 24fps math, run/stop frame count, lyrics/subtitles prompts

17:59 Quality/perf knobs: CRF, VRAM monitoring, and low-VRAM args recap

20:22 Review result + move to LTX 2 image→video preset workflow

21:50 Prompt enhancer workflow: drag prompt file into AI Studio (optionally add image)

24:11 Z-Image troubleshooting: disable Sage Attention and restart

24:32 Z-Image base + 2× upscale preset: when to use it and what to expect

26:47 Outputs & reproducibility: where renders save + drag PNG to reload metadata

27:57 Update SwarmUI via zip: get latest presets + utilities

28:27 SwarmUI setup: ComfyUI backend, passing args, and pointing to model folders