制作・メディア · GitHub

Wan 2.7 Image API (`wan2.7-image`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

Wan 2.7 Image prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`wan2.7-image`) and the cost per image.

Nano Banana API (`gemini-2.5-flash-image-preview`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

Nano Banana prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`gemini-2.5-flash-image-preview`) and the cost per image.

Ван — Wan 2.7 R2V API (`wan2.7-r2v`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

Ван — Wan 2.7 R2V prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`wan2.7-r2v`) and the cost per image.

The Programable Image Editor

• 🧱 Block-based canvas: code snippets, text, images, icons, shapes, freehand strokes, phone and browser mockups, QR codes and HTML blocks. Move, resize, rotate, crop and warp them, select several at once, align and distribute them, group them into layers and undo any change.
• ✏️ Drawing: a vector brush with pressure, shapes drawn by dragging, node editing, an eraser, rulers and snapping guides.

把任意故事自动变成完整图片素材、分镜、中文视听提示词与 API 清单的 Codex Skill

🎬 泡泡猫的影视工具 — AI 影视创作工作站：文生图、图生图、文生视频、图生视频、短剧剧本拆解与提示词专家。支持 Agnes / DeepSeek / Qwen / 豆包 / MiniMax / Ollama 六大厂商，全局浮层不堵对话框。