Turn a single photo of a person into a polished 15-second cinematic cooking tutorial. The skill first generates a high-end production reference sheet — character look, kitchen environment, and a 9-panel action board — then drives a continuous reference-to-video render that keeps the subject's face, outfit, and kitchen consistent across every frame.
\n| Name | \nType | \nRequired | \nDefault | \nDescription | \n
|---|---|---|---|---|
person_image | \nimage_url | \nyes | \n— | \nURL of the person photo. Used as identity reference in BOTH the reference sheet and the final video. | \n
dish | \ntext | \nno | \nfresh pasta | \nThe cooking subject (e.g. \"fresh pasta\", \"sushi rolls\", \"wood-fired pizza\", \"matcha latte\"). Drives the 9-step action board. | \n
kitchen_style | \ntext | \nno | \nwarm rustic-modern Italian | \nThe kitchen aesthetic (e.g. \"warm rustic-modern Italian\", \"minimalist Tokyo\", \"bright Scandinavian\", \"moody industrial\"). | \n
outfit | \ntext | \nno | \nwhite t-shirt, olive green apron, dark trousers | \nWhat the person wears throughout the video. | \n
duration_seconds | \nint | \nno | \n15 | \nFinal video duration. Use 15 for the full 9-step arc; 10 collapses to ~6 beats. | \n
aspect_ratio | \ntext | \nno | \n16:9 | \nOutput aspect ratio. Use 9:16 for vertical/Reels. | \n
resolution | \ntext | \nno | \n720p | \nVideo resolution. Options: 480p, 720p. | \n
Submit the plan with TWO sequential steps. Step 2 depends on the output of Step 1.
\nGenerate the composite \"production reference board\" image. This is a single image, NOT a video frame — it bundles character sheet + location reference + 9-panel action board.
\nEndpoint: gpt-image-v2-edit\nCLI:
muapi image edit \\\n --model gpt-image-v2-edit \\\n --image \"{{person_image}}\" \\\n --image-size \"3840x2160\" \\\n --quality auto \\\n --background auto \\\n --moderation low \\\n --output-format png \\\n --prompt \"Create one single composite reference sheet for a {{duration_seconds}}-second realistic {{dish}}-making tutorial video. The image should be a clean, high-end production reference board, not a poster with heavy text. Format: {{aspect_ratio}} wide reference sheet, elegant white margins, clean grid layout, realistic cinematic photography style. Concept: {{dish}} tutorial in a {{kitchen_style}} kitchen.\n\nTop row: motion / choreography guide with 9 numbered cinematic action panels showing the {{dish}} process step-by-step from raw ingredients to final plated dish.\n\nMiddle-left: realistic character reference sheet of the uploaded person — preserve their exact face, hair color, hair texture, eye color, skin tone, and all facial features with 100% accuracy. Show the same person in: face close-up, full-body front view, side/action working pose, and back view. Dress them in {{outfit}}. Keep them grounded, approachable, skilled, and cinematic.\n\nMiddle-right / background: location reference sheet of an elegant {{kitchen_style}} kitchen with tactile surfaces, natural daylight from a large window, hanging cookware, herbs, and premium cooking atmosphere appropriate to the cuisine.\n\nStyle: realistic, cinematic, warm natural light, shallow depth of field, tactile food photography, premium cooking show aesthetic, rich surface textures.\n\nBottom strip: simple visual icons only for {{duration_seconds}} seconds, {{aspect_ratio}}, realistic, cinematic, tasty, natural camera. Minimal text, no dense paragraphs. Let the visuals do the heavy lifting.\"\nWait for completion and capture the output URL as {{reference_sheet_url}}. Show it to the user and confirm the character likeness + kitchen mood before moving to Step 2 — Step 2 is the expensive call.
Animate the full sequence using both the original person photo (identity anchor) and the reference sheet (narrative + environment guide) as dual references.
\nEndpoint: bytedance-seedance-2-0-reference-to-video-fast\nCLI:
muapi video generate \\\n --model bytedance-seedance-2-0-reference-to-video-fast \\\n --image \"{{person_image}}\" \\\n --image \"{{reference_sheet_url}}\" \\\n --aspect-ratio \"{{aspect_ratio}}\" \\\n --duration \"{{duration_seconds}}\" \\\n --resolution \"{{resolution}}\" \\\n --generate-audio true \\\n --prompt \"The person in @Image1 is the subject — preserve their exact face, hair, eye color, skin tone, and all facial features with 100% accuracy throughout the entire video.\nUse @Image2 as the visual and narrative guide — follow the cooking steps, kitchen setting, outfit, and atmosphere shown in the reference sheet exactly.\nA single continuous cinematic video of the person from @Image1 making {{dish}} in the {{kitchen_style}} kitchen shown in @Image2. They wear {{outfit}} throughout.\n\nVIDEO STRUCTURE\nFollow the exact 9-step sequence as shown in @Image2, beat by beat, from raw ingredients through preparation to a final plated close-up.\n\nMOTION STYLE\n- Slow, deliberate, satisfying transitions between each step\n- Natural hand and body movement with clear culinary intent\n- Continuous flow with no jump cuts\n- Warm and immersive pacing\n\nCAMERA & CINEMATOGRAPHY\n- Close-up shots for hands during mixing, kneading, cutting, plating\n- Medium shots showing the person working at the counter\n- Pull back slightly for the final plating to reveal the full kitchen\n- Shallow depth of field — focus on hands and food, soft background blur\n- No abrupt cuts — smooth match cuts and fluid transitions\n\nVISUAL STYLE\n- Warm natural daylight from a large kitchen window\n- Rich tactile textures matching @Image2's environment\n- Full color, warm cinematic color grading\n\nCONSISTENCY RULES\n- Same character throughout — face of @Image1 in every frame\n- Same outfit across entire video\n- Same kitchen environment as shown in @Image2\n\nAUDIO\n- Soft kitchen ambience, gentle culinary SFX (chopping, sizzling, pouring), light cinematic underscore\n- No dialogue, no narration\n\nOUTPUT STYLE\n- Duration: exactly {{duration_seconds}} seconds\n- Polished, cinematic, premium cooking show quality\n- Ends with a beautiful close-up of the finished plated {{dish}}\"\nAfter generation:
\n{{dish}} for a different cuisine using the same person image.@Image1 locks identity, @Image2 locks choreography + environment. Never drop one — single-reference runs lose either the face or the kitchen.bytedance-seedance-2-0-reference-to-video-fast natively generates audio when generate_audio=true. Always include an audio direction in the prompt; otherwise the soundtrack is random.{{dish}} and the 9-step description change.cooking video, cooking tutorial, pasta video, recipe video, food video, chef video, cooking storyboard, kitchen tutorial, cooking reel, tutorial video from photo, storyboard to video
muapi CLI commands. Use muapi auth configure first if MUAPI_API_KEY is unset.curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H \"x-api-key: $MUAPI_API_KEY\" -H 'content-type: application/json' -d '{...}' and poll with muapi predict wait <request_id>.{{input_name}} placeholders with the user's actual inputs before issuing each call.--image to the video step.