Output of the ltxv-2b-0.9.6-dev-04-25.safetensors I2V is glitchi as hell and for T2V some alien fingers are "around"...Pls advice!

[zappazack]

I2V: Output of the ltxv-2b-0.9.6-dev-04-25.safetensors I2V is glitchi as hell! Pls advice!

Metadata in the videos.

https://github.com/user-attachments/assets/94b45e2c-91de-464c-a482-8734045717c9

https://github.com/user-attachments/assets/46c09514-292f-4b6b-a7a2-9166a97849e1

T2V:

https://github.com/user-attachments/assets/afa57349-b6e6-4612-9721-152e909804fd

[1blackbar]

distilled version works better

[zappazack]

distilled version works better

I will try thx

[zappazack]

distilled version works better

Sadly not relly...any idea?

https://github.com/user-attachments/assets/b8017b45-e32e-4a33-8872-594e0d22c946

[michaellightricks]

Note that distilled version has its own flow and regular i2v flow can't be used with it, did you use the distilled version flow? For the full model please try to reduce the value of img_compression parameter in the LTXVPreprocess node.

[zappazack]

Note that distilled version has its own flow and regular i2v flow can't be used with it, did you use the distilled version flow? For the full model please try to reduce the value of img_compression parameter in the LTXVPreprocess node.

Thx I have used the example wfs from the repo. Are there any other wfs?