nice job!
That conversion was way more complicated than I had thought, nice job!
I wasn't aware it was you who made the cine-lora for cogvideox. It was really good! Will you try remaking it for LTX?
haven't played too much with LTX but its on my list. the dataset is technically ready, would just need to run it. Will try and hopefully get to it in the next week or so!
I applied this:
https://github.com/comfyanonymous/ComfyUI/issues/6531
And ended up with just a few keys not working:
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.0.attn.to_k.lora_A.weight
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.0.attn.to_k.lora_B.weight
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.0.attn.to_out.0.lora_A.weight
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.0.attn.to_out.0.lora_B.weight
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.0.attn.to_q.lora_A.weight
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.0.attn.to_q.lora_B.weight
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.0.attn.to_v.lora_A.weight
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.0.attn.to_v.lora_B.weight
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.1.attn.to_k.lora_A.weight
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.1.attn.to_k.lora_B.weight
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.1.attn.to_out.0.lora_A.weight
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.1.attn.to_out.0.lora_B.weight
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.1.attn.to_q.lora_A.weight
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.1.attn.to_q.lora_B.weight
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.1.attn.to_v.lora_A.weight
lora key not loaded: transformer.context_embedder.token_refiner.refiner_blocks.1.attn.to_v.lora_B.weight
The (my) lora works great with this.