ChatGPT made a storyboard from a single reference image, then I used Seedance 2.0 to animate the storyboard shots:

Her card gets declined at the corner bodega. A stranger covers it. She passes the kindness on before the block ends. 30s AI microdrama, one character reference image → a timestamped shot-list prompt in Seedance 2.5 → upscaled with Topaz Astra 2. "Exact Change" 🧃

Retweet if your team is one of the 22 remaining undefeated teams

Same motion, new worlds 🎬 One clip → a depth map → Seedance 2.5 on @magnific Style transfer on the left, a full character swap on the right Every run, jump and swing is from the original clip:

if you told my 2023 self, this was done with our tools I wouldn’t have believed you from releasing Pikaso to now, the change is insane specially love how creativity has evolved too kudos to Heather for her work and contribution to the @magnific community always 🫶🏻

One clip from a wizard duel Claude Opus 5.5 built in code (top left), run through 3 video-to-video models to make it photoreal. Runway Aleph 2 kept the camera move and the choreography. Gemini Omni looked the most epic, but it added a second red wizard and threw out the camera. Seedance 2.5 barely changed it. None of them nailed it.

Kling 4.0 Flash held a character together for 15 straight seconds. Two clips chained gave me this 30s shot. 🦊💧 → Her face, freckles, orange streaks and tunic stay on-model through each clip → The water fox is translucent and glowing, the kind of subject that usually melts into mush. Here it trots, leaps and lands intact → About 90 seconds per 15s render How: one keyframe from my character sheet → 15s clip → its last frame starts clip 2 → joined into one shot. All run from Claude Code through the @Kling_ai MCP. What should she discover next? 👇

Moodboard: Expressive Marker → Krea 2 in @krea_ai

Midjourney v8.2 --sref 3159569084 2847267330

Introducing the "Geo Method" - A way of filmmaking that tethers AI video to something physically real, and unmistakably human. Our method bridges traditional cinema and the incredibly impressive AI future. "Geo" represents earth, ground, geometry, location. How it works: we build scenes and sets as physical miniatures, hand-crafted, lit, and shot practical on cinema cameras and lenses. That footage becomes our source plate: a live-action anchor with real light, real depth, and real texture that brings unmatched intention and direction to the generative AI process. Then, inside our proprietary software ("ST00DIO"), we bring the plate to life with additional elements. Our mixture of original 3D models and AI-generated assets are integrated into the scene, giving us greater control over performance and animation, directed by humans. AI handles relighting, asset-based set extensions, and atmosphere, but the world itself is born from photographic live action. The final piece is our "Shot Composer" tool for micro adjustments if needed, or entirely new scene framing. From a single still frame from the miniature capture source plate, it generates procedural geometry and a matching, fully directable virtual camera. From there, if we desire, we can further direct the shot with precise control: camera moves that were never physically possible on the practical tabletop, specific composition rebuilds, and explicit blocking for animated characters, then render the new result against the original live-action plate (video). What you get is a true hybrid production for AI animation: the grounded realism of practical miniatures with the creative freedom and speed of AI. The scene is real. The camera becomes editable. The visual effects are picture-perfect. The storytelling is human-led. The Geo Method. Developed at m00m Studios (@m00m_w0rld) by Jordan Freda and Ben Lam.

Experimenting with animating srefs in Midjourney alpha ✨ --sref 3159569084 Sound & text added in Claude Opus 5.5:

Claude Opus 5.5 working audio + video signal processing 🔥 sight + sound = vibe

The prop is drinking the props 🫖 A little on-set mischief with Seedance 2.5, starting from one image. Keeping the tea level consistent gets tricky when the fox on the cup helps himself.

Using Opus 5.5 for my website promo

Going back to old storyboards to see how Opus 5.5 improves ideas This one used @magnific MCP in Claude Code