Frame-to-Frame Pour · skill pubblica Open Skill
Frame-to-Frame Pour
Frame-to-Frame Pour è una Open Skill pubblica su Digen. Aprila per vedere cosa crea questo workflow.
Product
1 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284958/2026-10-16/a6z2fg5g.webp
# Frame-to-Frame Pour Physics, politely ignored. A sharp-suited man leans out of one ornate gold frame and pours a drink in a continuous stream into a glass mug held by the same man in the frame below, ending in a joyful splash. ## When to use - The user wants a photographic illusion where a man pours a drink from one picture frame into a glass in another frame below (cross-frame pour, beverage illusion ad, two-frame splash photo) - A variation on a previous result: sparkling cola Not for: Video output (use a video skill). ## Inputs and gates | Input | Required | Default | Gate | |---|---|---|---| | Person photo | No | — | Optional; if given, the face is preserved | | Beverage bottle | No | — | photo of the bottle to reproduce | | Description | No | tuned default below | What the user wants; merged into the prompt | | Beverage | No | `amber craft soda` | amber craft soda (default), sparkling cola, iced lemon tea, or user-described | | Ratio | No | `3:4 default` | 3:4 default; 2:3, 9:16 on request | - If the person may be under 18, stop and decline politely. Real-person photos must be of adults the user has the right to use. - Fashion, dark and horror themes are fine as stills; refuse explicit sexual content and anything sexualizing minors. ## Steps 1. Read `references/image-edit.md` for prompt structure. 2. Fill the template below from the user's description. Use the tuned defaults for anything they leave out; ask one short question only if the subject itself is unclear. 3. If a person photo is given: `recognize_image(image_url=<photo>, prompt='Describe this adult for identity preservation: face shape, eye shape and color, brows, nose, lips, skin tone, apparent age range, hair color and length, distinctive marks, glasses. One compact line.')` and add the identity clause. 4. With reference images: `generate_image(prompt=<PROMPT>, input_urls=[refs...], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Frame-to-Frame Pour', entity_type='skill_generation')`; without: the same call with `model='t2i.hd'` and no `input_urls`. 5. **Self-check, one retry**: look at the result. If a person photo was used and the face no longer reads as the same person, regenerate with the identity clause first. If someone glancing at it would not instantly see the intended change (it reads as a light filter, the old clothes or background remain, or the style is faint), regenerate once with the change described bigger and more concretely. 6. Reply in one or two sentences, e.g. "All set. Your frame-to-frame pour is on the canvas. Next I can do sparkling cola." Results appear on the canvas; never paste URLs. ## Prompt templates **PROMPT** ```text <if photo: The same adult from the reference: <identity line>.> Intentional changes: a photographic illusion with two ornate gilded picture frames stacked vertically on a dark wall against a softly blurred night city skyline: in the upper frame <man: from the person photo if given, else a stylish man in his thirties with a trimmed beard> in <suit: a tailored navy three-piece suit (default) or user-described> leans out and tilts an unbranded glass bottle of <beverage: amber craft soda (default) or user-described>, a continuous glossy stream falling across the gap between the frames; in the lower frame the very same man smiles and holds a glass mug catching the stream in a joyful splash with flying droplets; both appearances are clearly the same person, sharp product-photography lighting with rim highlights on the liquid, realistic reflections, cinematic commercial finish, no logos. <user details and options>. Clear focal hierarchy; any text short, in quotes and spelled exactly; no real brands. Lighting and materials described concretely; composition suited to portrait 3:4. Photoreal unless the style says otherwise, fully clothed, no text unless requested. ``` Quality bar: Keep on-image text short and in quotes; no real brand names or logos; one clear focal hierarchy. ## Failure handlin