LTX-2.x 24h Signals
11 LTX-2.x thread(s) in the last 24h. Highest-signal items center on workflow tuning and practical generation issues.
Models
- Is it normal for LTX 2.3 on WAN2GP to take more than 20 minutes just to load the model? I have 16 GB Vram and 64 GB ram — 5↑, 9 comments
Tools/Workflows
- Can anyone share their LTX2 / 2.3 configs for ai toolkit lora character training using images only? — 6↑, 2 comments
- How do i install missing custom nodes from the official LTX 2.3 workflow in ComfyUI? — 2↑, 14 comments
- LTX 2.3 ComfyUI parameters? — 0↑, 1 comments
Resources
- LTX 2.2 was nice but just not good enough. But I really think LTX 2.3 has finally gotten me to where I’ve basically stopped using WAN 2.2 — 71↑, 90 comments
- Built a local AI creative suite for Windows, thought you might find it useful — 10↑, 20 comments
- LTX 2.3 - can get WF in a bit, WIP — 7↑, 0 comments
- LTX 2.3 + Qwen Edit — 4↑, 2 comments
- mom, ltx i2v got into the shrooms again!! — 3↑, 6 comments
- LTX 2.3 Body Horror - Lack of human understanding — 2↑, 4 comments
- Does anyone know what the second pass is on LTX 2.3 on WAN2GP and why it’s only 3 steps? Is that why all my outputs are mushy in motion? Would increase the steps fix that? — 1↑, 3 comments