🚀 Automated LoRA Studio — turn your videos into custom motion LoRAs.
Upload a video, choose a supported Wan or LTX model, describe the movement, and click Prepare + train.
The app automates:
- ✂️ Cutting and formatting training clips
- ✅ Frame count, size and FPS checks
- ✍️ AI captions you can review and edit
- ⚙️ Training caches and trainer setup
- 💾 Checkpoints, resume, supported previews and export
It brings together work you’d otherwise split between AI Video Clipper, manual FFmpeg commands, captioning tools and separate Wan/LTX training interfaces.
No coding or manual training configs needed for the built-in workflow. Designed to make video LoRA creation approachable without technical experience.
Free and open source. Your footage stays local. Compatible training hardware required.
👉 Get github.com/manat0912/automated-…
#lora
Browse tags
Most posts · Last 30 days
No recent tagged posts yet.
Phosphene 3.7.0 - drafts in a minute, a real 10 seconds, and LoRAs for Hailuo H3
Phosphene 3.7.0 is out - the workflow release for Hailuo H3. Drafts in about a minute. Draft tiers now decode through a tiny fast decoder instead of H3's full 36-layer decoder - the single biggest fixed cost in a render. A 640x384 5-second draft lands in roughly a minute; a full 10-second single-pass draft measured at 5:05 on an M4 Max. Delivery tiers keep the untouched decoder, so nothing you ship is affected. A real 10 seconds. "10s single pass" now sits next to the chained 10s on every canvas up to Native 1344x768. One window: no seam, no repeated action after 5 seconds, no drift between ha
You’re all caught up.
Join the community
Follow people and apps for updates. Explore Announcements and All for more.
Discover people →
