Taste my coffee · skill pubblica Open Skill
Taste my coffee
Taste my coffee è una Open Skill pubblica su Digen. Aprila per vedere cosa crea questo workflow.
Series
13 0 8
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4167672/2026-10-06/94evv5cj.png
# Barista Model Video Turn the user's model photo into a short video of her working as a barista in a tasteful apron uniform, serving a drink to a customer with warm, flirty-but-appropriate energy. ## When to use - The user wants a video of their model as a barista in an apron uniform serving a drink to a young man/customer. - The user wants to redo, tweak, or continue one of these barista model videos. ## Preset asset - `model_photo`: the user's model reference photo (used as the reference image for identity consistency). ## Steps 1. Confirm the user's intent and any specifics (drink type, apron color, tone of the interaction, portrait vs landscape). Default to `orientation='portrait'` (9:16) unless they ask otherwise. 2. Generate the video with `generate_video`: - `model='ref2v'` (reference-to-video, keeps the model's identity consistent) - `input_urls=[model_photo]` (the preset asset, or the user's uploaded photo) - `prompt`: describe the scene in English — the model as a barista wearing a tasteful, fully-covering apron uniform over a modest top, standing behind a coffee bar, warmly handing a freshly made drink to a young man customer, friendly eye contact, warm and flirty-but-appropriate energy, cozy cafe lighting, natural motion. - `orientation='portrait'` (9:16) by default - `resolution='720P'` default - `name`: e.g. "Barista serve — take 1" - `entity_type='ref_videos'` 3. If the user wants multiple clips stitched together, generate each clip with `generate_video` (same `entity_type='ref_videos'`), then combine them with `mix_clips` (`entity_type='final_videos'`). 4. Report the result in natural language; do not paste raw URLs. ## Notes - Keep the content tasteful and appropriate: the apron uniform must fully cover the model. Politely decline any request for nudity, revealing outfits, or sexual content — video generation does not support NSFW/adult content on any channel. - Report failures honestly; never fabricate URLs. - Intermediate step-by-step products will be visible on the canvas.