Image - 2026-08-12 12:09
Create the next scene using the exact same mother and baby character references from the previous scenes. STRICT CHARACTER AND OBJECT CONSISTENCY: Keep the mother and baby absolutely identical to the reference images and previous frames. Do not change their faces, facial features, hairstyles, hair colors, clothes, body proportions, age or character design. OBJECT CONSISTENCY: There is EXACTLY ONE SPOON in the entire scene. The ONLY spoon is in the baby's hand. Do NOT create, add, duplicate or show any second or third spoon. No extra utensils, no forks, no additional feeding tools. SCENE: The baby is sitting in his high chair and holding the single spoon by himself. The baby has already made a big mess while trying to eat: - visible baby food is smeared on both cheeks - a small amount of baby food is clearly visible on the baby's nose - baby food is visible around the baby's mouth - several small and medium splashes of baby food are clearly scattered across the tabletop - a few small food stains are visible on the baby's hands - the mess must be clearly noticeable and visually important in the frame The mother reaches toward the baby's hand, trying to help him with the spoon. The baby pulls the spoon closer to himself and raises his free hand toward his mother, clearly showing the gesture: "I can do it myself!" The baby has a very serious, stubborn and determined expression. The mother freezes in surprise, looking at the baby with raised eyebrows and a slightly shocked but amused expression. IMPORTANT VISUAL PRIORITY: The messy baby food on the baby's face AND the scattered baby food on the table must be clearly visible. Do not clean the baby or the table. Do not make the table clean or spotless. Keep the same bright cozy kitchen, same dining table, same lighting, same environment and same color palette as the previous frames. High-end cinematic 3D animated family movie aesthetic, expressive facial animation, cute exaggerated emotions, realistic food texture, soft shadows, vibrant colors, detailed materials. Medium-wide shot, camera positioned slightly above table level so both the baby's messy face and the messy tabletop are clearly visible. Vertical 9:16 composition. NO TEXT. NO SUBTITLES. NO EXTRA CHARACTERS. NO EXTRA SPOONS. NO DUPLICATE OBJECTS. NO CLEAN TABLE. NO CLEAN BABY.
Free to start · Generate videos and images with AI in seconds