LTX 2.5 I2V and FLF 2V
LC123 Nodes: https://github.com/lonecatone23/ComfyUI_LC123_nodes
也有中文说明
Instagram: https://www.instagram.com/synth.studio.models/
Buy me a☕ https://ko-fi.com/lonecatone
This represents manyof hours of work that I give away for free. If you enjoy it, Please make sure to 👍like and post to my workflows. That is how you support me!!! Also, feel free to ⚡tip 😉
Note: If you have ANY issues with nodes not downloading, read the notes or reach out. There's nothing that special about any of them that aren't core modules. Most issues can be resolved by updating everything
This is a pretty solid model. I like it. It is clear and fast.
Notes: I'm really not impressed with the LLM. It made the words repeat itself, even after messing with repetition penalty and jacking up the cfg. I'll see what I can do next go around. If anyone has any ideas, let me know.
The FLF2V works pretty well. I put some notes in that area. It needs some dialing in. It took me 4 runs to get the results I wanted, but even so it smokes WAN2.2
Description
FLF2V
FAQ
Comments (5)
I am getting some strange ghosting in the renders, any idea why? thank you for your work.
I use the distilled model not the unet
I have no clue. I know very little about this model. It's probably a model issue as ghosting happens a lot when the audio and video latent do not align.
Check to see if you are using a compatible Clip
works really well! interested to see the adoption rate for ltx2.5
Prompt adherence is weaker than MiniMax. I think the quality is better though.
I dunno. I choose MiniMax right now
@lonecatone23 yeh, looks like minimax is probably going to win out in the end. at least for NSFW. I think i agree with you rn though