--- name: seedance-footage-vfx description: > Write, improve, or rewrite Seedance 2.5 prompts that TRANSFORM footage the user already has (video-to-video), rather than building a scene from scratch. Use whenever a real clip is the starting point and they want a Seedance prompt to: add a VFX element (set a head or hair on fire, transform a hand, make a limb invisible), swap the environment around a preserved subject (clouds, lava, a neon city), drop a giant photoreal creature onto a landmark, relight or regrade so the subject and added elements look like one shot, sync a crash zoom or push-in to a spoken line or timecode, or generate a matching transformed start frame to animate from. Also use when they paste such a prompt and ask to change its lighting, timing, creature, or runtime. Trigger even if they just say "make a Seedance prompt for this video" with a clip attached. This is the video-to-video specialization; for a brand-new scene from image references with no source clip to preserve, the general Seedance prompter applies instead. --- # Seedance 2.5 — Footage Transformation This skill is for **editing a clip the user already has**: keep a real subject and the real camera move, change only what they ask for. It is the video-to-video sibling of the general Seedance prompter. It reuses the same prompt grammar — a compact specs line, scene action written as a single continuous shot (the source is one take), an `SFX` line at the end, and a terse director's voice — and adds the transformation layer below. ## The core idea: preserve, then change one thing A transformation prompt has two jobs that pull against each other: **lock** everything that makes the source recognizable (the person's identity, face, wardrobe, performance, framing, lens, and camera motion), and **change** only the named element. If you under-specify the lock, Seedance re-rolls the face or the camera and the edit stops matching the original. So every prompt states both halves explicitly, and repeats the most fragile guardrail — usually **"face and identity unchanged"** — at the end of the action. ## Prompt anatomy (transform variant) ### 1. The `@source` declaration ``` @source: Original — . Preserve exactly; . ``` If a transformation needs a real texture the model keeps faking (an animal's fur, a specific face), add a **second input** as a texture reference: ``` @creature: Reference photo of a real — . Appearance and fur/skin texture reference only; ignore the photo's background and lighting. ``` Before writing `@source` for a clip you can open, **inspect it**: read its duration / fps / aspect and extract a few frames. Build `@source` and the specs runtime from what the footage actually shows — subject, wardrobe, framing, camera move, time of day — not from the user's one-line summary. ### 2. Specs line ``` Photoreal. . s. . NON-IP — generic , not based on any brand or character. . ``` - **Match the source runtime by default.** If the clip is 6s, the prompt is 6s. - **NON-IP guardrail** belongs in the specs line whenever a creature, armor, vehicle, or character design is added. - **Audio:** `SFX only` for added effects; `SFX and source dialogue only` when the source talk track must survive. ### 3. Scene action — one continuous shot The source is a single take, so describe **continuous camera movement**, not cuts. Lead with the shot/lens and "same framing as the source," then the preserved performance, then the transformation, then any timed camera move. Close with the lock-down clause. ### 4. SFX line End with a specific, ordered SFX note. For added effects be behavioral: not "fire" but "a soft whoomph as it catches, then a low steady flame roar and crackle, occasional ember pop." --- ## Two transformation modes ### A. Add an element to the footage Set a head on fire, transform a hand, make a limb invisible, perch a creature on a landmark. - Describe the effect's **physics and behavior over time**: where it starts, how it spreads, how it moves, what light it throws. - Make the effect **interact with the plate**: firelight flickering on a face; a glassy invisible arm refracting the background; a giant creature casting a real soft-edged contact shadow. - **Scale must be explicit** for giant creatures. Say "enormous, its massive body dwarfing the structure, clearly colossal relative to the mast." - The subject usually stays **oblivious / unfazed**, mid-delivery. ### B. Replace the environment around a preserved subject Keep the person, their vehicle, the camera rig and its move; swap the whole world. - The new world must **stream past with parallax** consistent with the original motion. - **Warm, directional daylight worlds are safer** for face/identity consistency than night or neon. --- ## Lighting integration First decide the fork: - **Preserve the subject's lighting, grade only the new elements.** Lowest identity risk. - **Relight the whole frame under one look.** Higher risk to the face, so keep identity explicitly locked while only lighting and grade change. When integrating a subject into a new world, go beyond color matching: - **Light:** same key direction, same softness, same shadow density across the subject. - **Environmental bounce:** cool skylight from above, warm bounce from sunlit ground. - **Optics:** match lens character; add atmospheric haze over the subject; match depth of field. - **Edges:** remove hard cut-out edges, halos and mismatched rims. --- ## Iterating Change **only the named thing** and keep the rest of the prompt stable. Re-rolling the whole prompt loses what already worked. When the camera drifts, describe its actual physical path (starting distance, height, direction, tilt angle) instead of just saying "don't change the camera." Specificity beats repetition. --- ## Output format Output in **English first**, plain text — no bold, no headers, no bullets inside the prompt, not in a code block. Easy to copy as-is. Skeleton: ``` @source: ... @creature: ... (only if a texture reference is used) Photoreal. 16:9. s. . NON-IP — generic . SFX [and source dialogue] only. SFX [and source dialogue] only: . ``` ## Seedance 2.5 input limits Images ≤ 9; videos ≤ 3 items, total ≤ 15s; audio ≤ 3 MP3s, total ≤ 15s; total mixed inputs ≤ 12; generation duration 4–15s.