{"slug":"muapi-multi-angle-reshoot","title":"muapi-multi-angle-reshoot","summary":"Re-render a subject or scene from multiple dramatic camera angles, such as fish-eye, bird's-eye, low-angle, and macro, while maintaining consistent identity and detail.","platform":"opencode","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-09-01T17:42:45.127325Z","repo":{"url":"https://github.com/SamurAIGPT/Generative-Media-Skills","stars":4295,"forks":492,"license":"MIT","updatedAt":"2026-09-08T23:14:35Z"},"bodyHtml":"<hr>\n<h2>slug: muapi-multi-angle-reshoot\nname: muapi-multi-angle-reshoot\nversion: \"1.0.0\"\ndescription: Re-render a subject or scene from multiple dramatic camera angles, such as fish-eye, bird's-eye, low-angle, and macro, while maintaining consistent identity and detail.\nacceptLicenseTerms: true</h2>\n<h1>Multi-Angle Reshoot</h1>\n<p><strong>Re-render a subject or scene from multiple dramatic camera angles, such as fish-eye, bird's-eye, low-angle, and macro, while maintaining consistent identity and detail.</strong></p>\n<h2>Inputs</h2>\n<table>\n<thead>\n<tr>\n<th style=\"text-align: left\">Name</th>\n<th style=\"text-align: left\">Type</th>\n<th style=\"text-align: left\">Required</th>\n<th style=\"text-align: left\">Default</th>\n<th style=\"text-align: left\">Description</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td style=\"text-align: left\"><code>subject_description</code></td>\n<td style=\"text-align: left\">text</td>\n<td style=\"text-align: left\">yes</td>\n<td style=\"text-align: left\">—</td>\n<td style=\"text-align: left\">Description of the subject or scene (e.g. \"a professional woman in a black suit holding a laptop\").</td>\n</tr>\n<tr>\n<td style=\"text-align: left\"><code>reference_image</code></td>\n<td style=\"text-align: left\">image_url</td>\n<td style=\"text-align: left\">no</td>\n<td style=\"text-align: left\">—</td>\n<td style=\"text-align: left\">Optional reference image to maintain consistency across angles.</td>\n</tr>\n</tbody>\n</table>\n<h2>Steps</h2>\n<h3>Phase A — Subject Establishment</h3>\n<p>If <code>{{reference_image}}</code> is not provided, submit the plan with ONE step to create the base subject:</p>\n<ol>\n<li><strong>Subject Generation</strong> — <code>muapi image generate</code> (model=<code>nano-banana-pro</code>):\n<ul>\n<li>Prompt: <code>A high-quality, professional photograph of {{subject_description}}. Clean studio lighting, sharp focus, realistic textures, cinematic quality.</code></li>\n<li>Aspect ratio: 3:4 or 1:1</li>\n</ul>\n</li>\n</ol>\n<p>Present the base image to the user for approval.</p>\n<h3>Phase B — Multi-Angle Reshoot</h3>\n<p>Once the subject is established, submit the plan using <code>muapi image edit</code> (model=<code>nano-banana-2-edit</code>) to generate the requested angles. Use the approved image from Phase A as the reference for ALL steps.</p>\n<ol>\n<li><strong>Bird's Eye View</strong>\n<ul>\n<li>Reference: Base Image</li>\n<li>Prompt: <code>A dramatic bird's eye view (from directly above) of the same subject. High-angle perspective, wide shot, looking down. Maintain exact clothing, face, and setting consistency.</code></li>\n</ul>\n</li>\n<li><strong>Fish Eye Lens</strong>\n<ul>\n<li>Reference: Base Image</li>\n<li>Prompt: <code>A high-distortion fish-eye lens photograph of the same subject. Ultra-wide angle, curved edges, dramatic perspective, immersive feel. Maintain exact clothing and face consistency.</code></li>\n</ul>\n</li>\n<li><strong>Low Angle (Hero Shot)</strong>\n<ul>\n<li>Reference: Base Image</li>\n<li>Prompt: <code>A low-angle \"hero shot\" looking up at the subject. Makes the subject appear powerful and dominant. Maintain exact clothing and face consistency.</code></li>\n</ul>\n</li>\n<li><strong>Dutch Angle</strong>\n<ul>\n<li>Reference: Base Image</li>\n<li>Prompt: <code>A stylized Dutch angle (tilted horizon) photograph of the same subject. Cinematic, slightly uneasy or dramatic vibe. Maintain exact clothing and face consistency.</code></li>\n</ul>\n</li>\n<li><strong>Macro Close-up</strong>\n<ul>\n<li>Reference: Base Image</li>\n<li>Prompt: <code>An extreme macro close-up focused on a specific detail of the subject (e.g., eyes, texture of the suit, or a feature of the laptop). Shallow depth of field, incredible detail. Maintain exact colors and textures.</code></li>\n</ul>\n</li>\n<li><strong>Worm's Eye View</strong>\n<ul>\n<li>Reference: Base Image</li>\n<li>Prompt: <code>A worm's eye view from ground level looking straight up at the subject. Dramatic vertical perspective. Maintain exact clothing and face consistency.</code></li>\n</ul>\n</li>\n</ol>\n<p>After generating the variations, present the multi-angle gallery to the user. You can also offer to generate specific individual angles based on their feedback.</p>\n<h2>Trigger Keywords</h2>\n<p><code>multi angle</code>, <code>photo reshoot</code>, <code>change camera angle</code>, <code>fish eye view</code>, <code>birds eye view</code>, <code>low angle shot</code>, <code>macro photography</code>, <code>camera perspective</code></p>\n<hr>\n<h2>Notes for the Executing Agent</h2>\n<ul>\n<li>This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call <code>muapi</code> CLI commands. Use <code>muapi auth configure</code> first if <code>MUAPI_API_KEY</code> is unset.</li>\n<li>For model IDs without a CLI alias yet, fall back to the raw endpoint via <code>curl -X POST https://api.muapi.ai/api/v1/&lt;endpoint&gt; -H \"x-api-key: $MUAPI_API_KEY\" -H 'content-type: application/json' -d '{...}'</code> and poll with <code>muapi predict wait &lt;request_id&gt;</code>.</li>\n<li>Substitute <code>{{input_name}}</code> placeholders with the user's actual inputs before issuing each call.</li>\n</ul>\n","files":[{"path":"SKILL.md","sizeBytes":3886,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-09-01T17:44:20.103199Z","sha256":"FB2B60E579C1144874BA146080045DEA148323653845B132EAFD44B84810273E","sizeBytes":1775},"review":null,"source":{"repositoryUrl":"https://github.com/SamurAIGPT/Generative-Media-Skills","path":"library/visual/multi-angle-reshoot","license":"MIT","commit":"5519622e885abc60217a65c8e090bcb1d9830746","subtreeSha":"30270C53CD8ED46C1435066C1C7B099DAF8DFA44E00C90164533C0F54BE6CD56","lastSyncedAt":"2026-09-18T12:16:43.426464Z"},"reviewedAt":"2026-09-01T17:48:03.620469Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/SamurAIGPT/Generative-Media-Skills/tree/main/library/visual/multi-angle-reshoot"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install samuraigpt-generative-media-skills@llmmart"},{"target":"git","command":"git clone https://github.com/SamurAIGPT/Generative-Media-Skills.git"}]}