Another little something, I worked on https://youtu.be/l9QCHpF_DU0?si=EjoouM_uvbbVA_1N

A little something for the new year 2026

I used the Nano-banana Pro AI image generator. I uploaded the background image and the character image as reference images. And I created the combined image using the enhanced prompt: "Create a full‑body, front‑facing cartoon character illustration of a young girl centered on a living room background in a clean flat vector style. Big round head (about one third of body height) with pastel sky‑blue long hair that sweeps in soft waves and a side part, subtle lighter highlights and smooth gradient shading. Large expressive green/teal eyes with big black pupils, white highlight glints, long upper eyelashes and thin eyebrows; small button nose, tiny closed smile, and soft rosy blush on cheeks. Slim elongated limbs and very thin long legs, simple hands with open palms slightly turned outward and arms relaxed at her sides. Outfit: white sleeveless sailor top with a blue v‑collar and thin white stripe, paired with a short pleated navy blue skirt with a white hem stripe; matching blue rounded flats with low heels. Colors: pastel skin tone, soft sky blues, navy accents, peach skin, bright green eyes. Lighting: soft even studio lighting with minimal shadows, gentle gradients for depth and subtle rim highlight on hair for dimension. Art techniques: crisp vector shapes, smooth outlines, minimal linework, flat cel shading with subtle gradients, high contrast between large shapes and clean negative space. Composition: centered full‑body portrait, straight-on camera angle, unobstructed white negative space around character. Output should look like a modern children’s cartoon character design, high resolution suitable for vector export (clean shapes, layered, 300 dpi)." After it was complete, I selected the "AI Video Generator" option from the dropdown menu in the top right corner of the image. In the AI Video Generator, I used the prompt: "Retain the exact same flat 2D animation style at in the image. The image is of a soft-lit living room at sunset; the camera follows the young girl in a gentle tracking shot as she turns her back to the lens and walks gracefully toward a plush sofa. In one fluid motion, the camera pans around to capture her turning to face the camera before sitting down, framed in warm cinematic lighting with shallow depth of field" (I also used the "improve prompt" option).

I am thinking about an upcoming story in a 2D animation style which involves dinosaur toys coming to life. I have been trying to figure out how to do it using my established characters, and it occurred to me maybe I could just do the dino toys/characters in AI with a chromakey background (blue in this case), then key them into scenes I will animate in Cartoon Animator. So, for example, the characters (kids) are playing with dino toys, something magical happens, and the toys come to life, grow huge, and escape. Then the kids have to track down the dinos and magically turn them back into toys. Here's an experiment with a T-Rex coming to life and exiting screen right. First I created the character in nano banana, created different poses (front/side/back), then created this animation using Veo 3.1 Fast. It took multiple tries to get this right - it kept adding details I didn't describe. It also struggled to understand that I wanted the dino to exit screen right. I had uploaded the first frame, but realized I had to also upload a final frame with just the blue background, no dino. When I did that, it worked. It's not exactly what I was imagining, but pretty close. This took about 3 million credits, all told. 😬 Oh, yeah... and the footsteps are hilariously wrong. I would replace the sound on this clip with much better sounds.

I used the "improve prompt" option on my prompt "Girl in the "lollipop girl" reference image turns and walks to the sofa in the "living room" reference image and sits down", and got this: "A soft-lit living room at sunset; the camera follows the young girl in a gentle tracking shot as she turns her back to the lens and walks gracefully toward a plush sofa. In one fluid motion, the camera pans around to capture her turning to face the camera before sitting down, framed in warm cinematic lighting with shallow depth of field." And this is the video it generated: