Text to Video AI Runway ML Gen2 - Chameleon

I've been testing the new Gen2 text to video AI model from Runway ML which is available for the public. Bare in mind this sample I made is text to video, may work far better on image to video.
The prompt for these clips were variations of the following:
"close-up of a panther chameleon in extreme detail, keep subject in focus, do not morph texture, do not flicker, national geographic footage"
Varied between Macro and 35mm styles, tried different camera animation settings.
We can see that there still is a lot to evolve on Runway ML`s Gen2 text to video AI when it comes to anatomy, continuity and animation. I did manage to get a decent looking chameleon in most shots, however the first frame is usually the best, and it goes downhill from there. I tried to make a moving chameleon but wasn`t able, may work better using an image other than text, or image + text.
I will make more tests focused on other subjects such as human portraits, landscapes etc. during the following weeks. I believe it may work well with landscapes especially image to video, other than text to video.