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