Skip to main content
Glama

generate_turnaround

Create consistent front, left, back, and right turnaround views from a concept image or prompt; use mesh guidance for flat or winged objects.

Instructions

Make consistent turnaround views of one object (front, left, back and right) from a concept image.

Give concept_image (a local PNG or JPEG of the object, any angle), or only prompt to generate the concept first with the image model. subject: a few words naming the object and its key parts ("a salvage robot with a cargo cage on its back and tread feet"); it goes into every view's prompt and defaults to prompt. Naming the parts helps them appear in every view. FLUX.2 Klein first redraws the concept as a clean front view (flat even lighting, no cast shadows, plain background). Views follow Pixal3D's rig: the left view shows the object's own left side, facing image-left. guide="none" (default, better for standing objects): each other view is drawn from the clean front and the concept from an empty latent, then scaled by silhouette height (which assumes a standing object seen level). Flat, winged or wide objects tend to come out facing the camera in every view (a moth with its wings spread flat in the side views). guide="mesh" (for flat, winged or wide objects): TRELLIS.2 meshes the clean front view (a guide mesh; guide_source="concept" meshes the concept instead, and a failure from the front retries from the concept), Blender renders it from the rig's cameras (turned by guide_yaw, found by matching the mesh to that image, since TRELLIS.2 does not always face a mesh's front to the rig's front), and Klein repaints each render image to image (guide_denoise, default 0.6, 0.3 to 0.95: lower keeps more of the render) with the clean front and the concept as references. The renders fix each view's pose and silhouette, so a moth's wings are edge-on from the side, and the views come out already framed for the rig. The views are only as right as TRELLIS.2's guess at the hidden sides: on a robot it copied the face onto the back, which guide="none" got right. three_quarter=True adds front_left, back_left, back_right and front_right views (for reference; meshing uses the four main views). symmetric=True draws only the left-hand views and mirrors them into the right-hand ones, which keeps a left-right symmetric object consistent (do not use it for asymmetric objects). Every view is square, the object centred at one scale, the widest view at 1/1.1 of the frame. Views are RGBA PNGs (alpha is a BiRefNet foreground mask) on background; a sheet puts them side by side. mesh=True also meshes the four views with generate_mesh's multi-view path (framing "as_framed"). Views are generated, so they can still disagree on details: look at them before relying on them. Returns the view paths by name, the sheet, the concept, the clean front, and with guide="mesh" the guide mesh ("guide_mesh", a usable single view TRELLIS.2 mesh on its own) and its renders ("guide_renders"); with guide="none" the raw (unframed) views; the mesh result when asked. About 6 s per view warm plus model loads; guide="mesh" adds a TRELLIS.2 run (about 1 to 2 minutes) and the Blender renders (about 10 s per view on the CPU).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "generate_turnaround"
  }
}

Input Schema

NameRequiredDescriptionDefault
meshNo
seedNo
guideNonone
stepsNo
promptNo
subjectNo
symmetricNo
view_sizeNo
backgroundNo#d8d8d8
output_dirNo
guide_sourceNofront
concept_imageNo
guide_denoiseNo
three_quarterNo
idle_timeout_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full behavioral burden and does so well: it names the pipeline stages (FLUX.2 Klein redraw, optional TRELLIS.2 mesh, Blender renders, BiRefNet alpha mask), discloses limits ('only as right as TRELLIS.2's guess at the hidden sides', 'views can still disagree on details: look at them before relying on them'), and gives timing (~6 s/view warm, 1-2 min for guide="mesh").

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose, then organized around the decision that matters (guide mode), exactly the right order. It is long and the guide="mesh" paragraph is a dense run-on that would read better as a list, but nearly every clause carries decision-relevant information rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter, annotation-free tool with no output schema, it is unusually complete: return values are enumerated by name (view paths, sheet, concept, clean front, guide_mesh, guide_renders), output format and framing rules are specified, and cost is estimated. The only real hole is the silent set -- seed, steps, view_size, output_dir, idle_timeout_seconds -- which an agent must guess at or ignore.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% across 15 parameters, and the description rescues most of the consequential ones with real semantics and defaults: concept_image, prompt, subject (with a modeling tip and default-to-prompt behavior), guide, guide_source (front/concept plus retry behavior), guide_denoise (0.6 default, 0.3-0.95 with directional meaning), three_quarter, symmetric, background, mesh. Five parameters -- seed, steps, view_size, output_dir, idle_timeout_seconds -- are never mentioned, so it falls short of full compensation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and deliverable: 'Make consistent turnaround views of one object (front, left, back and right) from a concept image.' The scope (four rig views, optional three-quarter set) is unmistakable and clearly distinct from the single-image and mesh siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use/when-not guidance throughout: guide="none" is 'default, better for standing objects' with a named failure mode, guide="mesh" is 'for flat, winged or wide objects', and symmetric carries an explicit prohibition ('do not use it for asymmetric objects'). It also explains the concept_image-or-prompt fork and the retry path when the front mesh fails.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.