0:29Nano Banana was the preview of Google’s new Gemini 2.5 Flash Image model. 🍌 I was given early access on @googleaistudio and created this video based off of 1️⃣ image I was really impressed by how it maintained consistency on the character as well as small details. (Pay attention to his shirt and hMMetaPuppet350KX
0:47Finally taking @Kling_ai 2.0 for a spin. The motion and physics are a game changer. Here is DOGFIGHT.IRIsaac Rodriguez75.9KX
0:34I got early access to the new @Hailuo_AI H3 model and they have cooked. I made this super short with just 5 image references (See below), it kept the artstyle intact changed the camera angels and followed my direction. The majority of this was made from two 15 second generations. It also looks to haUAUncanny Harry AI17.2KX
0:30Another @Hailuo_AI H3 test, this time looking at audio reference and performance (A little NSFW language on end of this one!). I recorded the dialogue as an audio track and fed that in as a reference with a image reference of the man. In the text prompts I gave some direction to the actor (Like theUAUncanny Harry AI15.4KX
0:30The doubters say you don't have control with AI video. This quick test with a blender animatic shows otherwise.. made with @magnific (for images) @dreamina_ai (for video) and @ElevenLabs (for voice).UAUncanny Harry AI2.6KX
0:30If this is where things are today, what will next year’s Super Bowl ads look like? We’re entering a very different creative era. As AI lowers the technical barrier this fast, ideas matter more than ever. I joined Dreamina AI CPP and got early access to use Dreamina Seedance 2.0. Dreamina SeedanceMMetaPuppet2.2KX
0:290:29
0:47
0:34
0:30
0:30
0:30
0:300:290:470:340:300:300:300:300:290:470:340:300:300:300:30