Advibly Collage Motion

One pipeline, two halves: analyze a reference into an editable spec, then build on-brand stills and assemble-from-empty motion. Everything runs on the Advibly MCP. The look is the halftone paper-collage / stop-motion-graphic editorial style: flat bold color field, halftone (printed-dot) elements, clean cut edges with a soft drop shadow between layers, one sharp idea per scene, and motion that builds the scene piece by piece instead of wobbling a finished frame.

Speak in the user's language. No em dashes anywhere in output; use periods or line breaks. Keep labels and copy free of emoji unless asked.

Hard defaults (do not drift)

• Image model: advibly_generate_image with model: "gpt-image-2" and quality: "high". gpt-image-2 follows a dense field-by-field spec faithfully, takes reference images, and is the strongest at native burned-in text, so scene labels hold without endless rerolls. If the paper-craft texture (dot pattern, cut edge, layer shadow, flat color) keeps flattening across rerolls, switch the whole set to nano-banana-2 (better texture retention, renders up to 4K); never mix image models across the texture-carrying frames of one set.
• Set shape: 4 scenes, 8 seconds per clip, by default. Each scene is one still pair (empty field plus finished composition) and one video clip. Only deviate when the user asks for a different count or length.
• Faithful color, not brand palette: pass on_brand: false. The decoded spec owns the color field and palette, so the brand-kit sheet must not be force-attached or it recolors the look. brand_id is still required on every generation call, and the run's project_id rides along on every call (together they file the work as one project tile in the user's library); neither styles the output when on_brand is false. Only set on_brand: true when the user explicitly wants the collage recolored to their brand.
• Video model: advibly_generate_video with model: "gemini-omni-flash" (8s or 10s per clip, 9:16 or 16:9, native audio). Omni Flash animates from a single start frame, so the default assembly opens on the empty-field still and the prompt drives the pieces sliding in. It has no end frame: when the clip must land on the exact finished composition, or you need 1:1 or a 15s duration, switch that set to seedance-2.0 (supports start_image_url + end_image_url for a mechanical empty-to-finished interpolation, plus all aspect ratios). See B3 for both routes. Pick one model per delivered set and stay on it.
• On-twos cadence is default-ON. Generate the source clips smoothly, then pass frame_cadence: "on_twos" to the final advibly_render_composition call. The editor and exported render will hold the visuals at about 12 unique frames per second while clip audio stays continuous. Skip it only when the user explicitly wants smooth paper motion.
• No text-overlay tool. Advibly has none by design. Scene labels are burned in at image generation by the image model. gpt-image-2 is strong at native text; if a label still keeps degrading, reroll with num_images (up to 4), simplify the label, or try seedream-5-pro for that one scene. Never plan to overlay text afterward.
• Tools are deferred. Load the exact Advibly tool schemas with tool search before the first call each session (search "advibly generate image", "advibly generate video", "advibly upload asset", "advibly list brands", "advibly create project", "advibly update project"). Confirm parameter names against what loads rather than assuming.