Character Turnaround Sheet Generator
Create orthographic multi-view character turnaround sheet from one reference image, keep consistent character features across front, side and back views, for sci-fi mech and armor character design.
例を試す
このワークフローについて
This workflow generates a clean, orthographic character turnaround (front, side, and back) from a single reference image—ideal for sci‑fi mechs and armor designs. It starts with LoadImage to bring in a front orthographic reference (a sample white_mech_front_ortho.png is included). That image is then passed to GeminiImage2Node, which calls a Google Generative image API and uses your text instructions plus the reference to synthesize additional angles while preserving key features like silhouette, plate layout, decals, and color scheme.
SaveImageAdvanced writes each view to disk with predictable filenames so you can assemble them into a final sheet in your design tool. A MarkdownNote in the graph provides inline guidance and prompt tips.
Technically, consistency across views is encouraged by conditioning GeminiImage2Node with the same reference image and carefully worded prompts (e.g., “orthographic side view of the same mech as the reference; match plating, helmet, and markings; no perspective; white background”). Because this template relies on an external API rather than local checkpoints, it’s quick to set up—no model downloads are required—making it a practical tool for concept artists and product designers who need fast, multi‑view explorations of a single design.
よくある質問
No. The core generation is handled by GeminiImage2Node via an external Google image API. You just need a valid API configuration; no local checkpoints are required.
Use the same reference image every time and keep prompts tightly scoped: specify “orthographic,” “no perspective,” and call out key elements to match (helmet shape, plating, decals, color). If results drift, tighten language (e.g., “exact same chest plate geometry and markings as the reference”) and keep background simple.
This template saves each view as a separate file via SaveImageAdvanced. You can assemble them in your editor, or add a tiling/composition step in ComfyUI if you prefer an all‑in‑one sheet.
It works for both, but hard‑surface designs tend to hold consistency more easily. For organic characters, be extra explicit about proportions, clothing details, and pose (neutral T‑pose, arms down, etc.).