agentsclimarketplace

Couple grid creator

Skill SamurAIGPT/Generative-Media-Skills/library/visual/couple-grid-creator

Create a stylized 6-box grid featuring a couple in various romantic poses and outfits, with each pose framed inside a unique cardboard box packaging.From its SKILL.md

Install
npx -y skills add SamurAIGPT/Generative-Media-Skills --skill couple-grid-creator

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

2.4 KB, 524 tokens by cl100k_base, as published. Nobody here has run it

Couple Grid Creator

Create a stylized 6-box grid featuring a couple in various romantic poses and outfits, with each pose framed inside a unique cardboard box packaging.

Inputs

NameTypeRequiredDefaultDescription
couple_imageimage_urlyesA clear photo of the couple to maintain identity.

Steps

Phase A — Multi-Pose Grid Generation

If {{couple_image}} is not provided, ask the user to upload a photo of the couple.

Once the photo is available, submit the plan with ONE step to generate the stylized grid:

  1. Grid Generationmuapi image edit (model=qwen-image-edit-plus):
    • Reference Image: {{couple_image}}
    • Prompt: Convert the above image into an 8k portrait of both faces. Both faces should be clearly visible inside separate packaging: brown square hollow cardboard boxes. There should be 6 big boxes fully occupying the frame in a grid layout. In each box, the couple's faces should be visible, striking different decent romantic poses. Each box should feature a different costume for the couple to differentiate the scenes, with both wearing decent western wear. The background inside each box should be solid black. Maintain strict identity consistency for both the man and the woman from the reference image. Cinematic tone, sharp focus, professional photography.
    • Aspect ratio: 1:1 or 4:5

Present the generated 6-box couple grid to the user.

Trigger Keywords

couple grid, romantic grid, packaging grid, couple photo box, stylized couple portrait


Notes for the Executing Agent

  • This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call muapi CLI commands. Use muapi auth configure first if MUAPI_API_KEY is unset.
  • For model IDs without a CLI alias yet, fall back to the raw endpoint via 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>.
  • Substitute {{input_name}} placeholders with the user's actual inputs before issuing each call.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.