Image-to-Video
Diffusion Single File
text-to-video
video-to-video
image-text-to-video
audio-to-video
text-to-audio
video-to-audio
audio-to-audio
text-to-audio-video
image-to-audio-video
image-text-to-audio-video
ltx-video
lightricks
comfyui
ltx-2.5
Instructions to use Lightricks/LTX-2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Lightricks/LTX-2.5 with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
The character consistency in i2v is a disaster.
#30
by lol104 - opened
Please fix this issue.
Thanks anyway for your great work. :-)
which model did you use?
which model did you use?
I tested with a photo (half portrait photo head to knees) of a European woman using LTX 2.3 and LTX 2.5 (without ID LoRa). Result: LTX 2.3 rendered the woman correctly, but with LTX 2.5, she looked completely different.
Finally, I tried a version with the ID LoRA "LTX-2.3-ID-LoRA-CelebVHQ-3K.safetensors." The result with LTX 2.5 was that the woman suddenly had an Asian face. I am MacUser (Macmini M4 pro, 25 GB RAM).
maybe the face id lora of ltx2.5 will fix it,just wait it
maybe the face id lora of ltx2.5 will fix it,just wait it
Is one planned? That would be wonderful :-)