Clean packshots from a real product photo

Connect the Scenario MCP

Connect your agent and sign in once at mcp.scenario.com. Then tell it which Scenario team and project to use, so every file lands there.

Give the agent the files

The sharp product photo with the wordmark facing the camera, then the photo of the inner side, then the back. The agent uploads them with upload_asset, or you give it their asset IDs. Keep that order: the front is the one every packshot is cut from.

Brief the agent: the flat set

Background tools keep the product's pixels; an image generator would redraw them. The brief says so, so the agent does not reach for one.

Make clean packshots from the product photo. Never generate or redraw the product: use only background and upscale tools, so every pixel of the wordmark comes from the photo. Read each model's parameters with model_schema_get first, then quote the cost with a dry run and wait for my go.

1. Pixelcut Product Photo (model_pixelcut-product-photo), three runs on the product photo, started together with wait: false and collected with one jobs_wait:
   - White: image size Square HD, background color red, green and blue at 255, margin 10%, shadow type Generative, generative shadow opacity 0.3.
   - Brand navy: image size landscape 4:3, background color red 28, green 38, blue 56, the rest as the white one.
   - Transparent: background transparent, generative shadow opacity 0.
2. When the white packshot is back: Topaz Image Upscale (model_topaz-image-upscale) on it, with enhanceModel "Text Refine" and upscaleFactor "2x".

Show me the four files with asset_display.

Check the wordmark at 1:1

Accept when the wordmark matches the photo letter for letter at 100 percent, the knit and the sole are the photo's own, the outline is clean on white and on a dark background, and the shadow sits under the sole. Reject any changed letter, lacing, sole or color, a white halo, or an edge that eats into the laces.

Download the four files with asset_download and compare each one with the product photo at 100 percent. Read the wordmark letter by letter, and look between the laces and around the sole for halos or a shadow on the wrong side of the light. Tell me which pass and which fail, and why. Redo only a file that fails, with the same settings.

The 3D model, from three views

From the cutout alone, the 3D run invented a garbled wordmark on the side it never saw. Give it the three views.

Now run Meshy 7.1 - Image to 3D (model_meshy-7-1-img23d) with image set to an array of three asset IDs, in this order: the transparent cutout, the inner side photo, the back photo. Settings: geometryResolution "2k", shouldTexture true, textureResolution "2k", enablePbr true, shouldRemesh true, targetPolycount 100000. Quote it with a dry run first and wait for my go. When it is back, show it to me and tell me if any letters, mirrored or not, appear on a side the photos did not show.

File the set and report

Turn the 3D model in the viewer yourself before you publish it.

Create a collection for this product and add the white, brand navy and transparent packshots, the 2x print version and the 3D model. Report the model used for each file, every asset ID and the total cost spent.

A cut-out model, not a generator

Choose a Model › Image › Remove Background › Pixelcut Product Photo, and add the product photo. Background tools keep the product's pixels; image generators redraw them, even when told "exactly".

White, for the marketplace

Image Size Square HD, Background Red, Green and Blue at 255, Margin 10%, Shadow Generative, Generative Shadow Opacity 0.3.

Brand color and transparent

Same model, same photo. Image Size landscape 4:3 with Background Red 28, Green 38, Blue 56 for the brand navy; then Background Transparent with Generative Shadow Opacity 0 for the cutout.

A print version with Text Refine

Open the white packshot › Enhance › Topaz Image Upscale, Model Text Refine, Scaling Factor 2x. It sharpens small type without inventing letter shapes.

Read the wordmark at 1:1

Check every file at 100 percent: read the wordmark letter by letter against the photo, and look between the laces and around the sole for halos. At thumbnail size a regenerated packshot looks the same.

Three views, not one

Create › 3D › Meshy 7.1 - Image to 3D, and under Image: the cutout, the inner side, then the back; geometry 2k, texture on with PBR, texture 2k, remesh on at 100,000. From the cutout alone it invented a garbled wordmark on the side it never saw.

File the set in one collection

Put the packshots, cutout and 3D model in one collection. Turn every 3D model in the viewer before you publish it.