LTX2.3-Mutiple-Subject-Reference (new IC lora model)
With this we can add multiple image references and make a video out of it. I did not test it yet because in his workflow he using not the transformer only model but the full distilled model with vae included and i have no space right now. Would be nice if u can add a new workflow for this great thing: https://huggingface.co/LiconStudio/LTX2.3-Mutiple-Subject-Reference
Looks very interesting for sure. Tried it, and works pretty well.
(and this is an early version lora, so it might even improve)
Will make a wf so its easy to try it out ;-)
(and the result in the video below is just a test run, probably not clear enough prompting since its a bit of leak between the characters.. only a first low res test run .. ;-)
Thank you so much <3. That would definitely be one of the best features in a long time. A major step toward cameos like in Sora 2—but not just that; it enables so much more if you can actually use multiple images as references. I love this community. Can't wait to try it with ur workflow.
Workflow added to try out https://huggingface.co/RuneXX/LTX-2.3-Workflows/discussions/167
Its an early test lora, so improvements might come. It's not a strong subject consistency .,.. yet. But a very promising lora for sure ;-)