I'm putting relevant stuff I find here since at the moment it's so spread all over the place it's hard to find the stuff that actually works.

If you have further suggestions just add them to the comments and lets try to centralize.

1.LTX Simple Distilled Image to Video

working ltx distilled image to video ltx-distilled-fp8.json (no freeze frames):

Very important!

In order for this to work reliably, you NEED to have a GOOD prompt; here's how to get it;

1. Take the starting image and drop it into any gpt

2. Put the prompt you want in and tell it: "Enrich this prompt starting from the provided image"

3. You should get something that is about the length of a raging twitter response that has the image details baked in (clothing, background, character description: hair etc)

4. You can of course use a VL node in comfy to achieve this as well:
   

   

Audio + Image to Video:

Really cool workflow adding existing audio to distilled workflow: https://civitai.com/models/2306894?modelVersionId=2595561