awesome-nano-banana-pro-prompts

Maintains a curated collection of 10,000+ image generation prompts organized across 16 language variants (English, Simplified Chinese, and 14 others) with auto-generated README files sourced from a Payload CMS instance. Uses TypeScript markdown-generator.ts to dynamically render localized README.md files from structured prompt metadata, enabling GitHub-native discovery without hand-editing. Each locale variant includes translated category taxonomies, featured prompts, and language-specific cover images.

Implements a structured contribution workflow where users submit new prompts via GitHub Issues using predefined templates, which are then validated, approved by maintainers, and automatically synced to Payload CMS via sync-approved-to-cms.ts. The pipeline includes image upload handling (image-uploader.ts) for preview assets and metadata enrichment before CMS persistence. Approval gates prevent unapproved prompts from appearing in generated README files or web gallery.

Provides a web-based interface (youmind.com/*/nano-banana-pro-prompts) for browsing the full 10,000+ prompt collection with search, filtering by category/style/subject/language, and one-click image generation via Nano Banana Pro API. The gallery is powered by CMS data and includes prompt preview images, metadata, and direct links to Raycast snippets. Supports pagination and sorting for large collections.

Executes TypeScript generate-readme.ts script (triggered by GitHub Actions) that fetches prompt metadata from Payload CMS, applies locale-specific transformations via i18n.ts, and renders 16 Markdown README files with translated category labels, featured prompts, and statistics blocks. The script reads CMS REST API responses, applies language-specific formatting rules, and commits generated files back to GitHub, ensuring README files always reflect current CMS state without manual editing.

Supports exporting prompts as Raycast snippets with dynamic argument placeholders that enable users to inject variables (e.g., {{subject}}, {{style}}) at runtime. Prompts are tagged with Raycast-compatible metadata in CMS, and the web gallery generates snippet export links that populate Raycast's local snippet manager with pre-configured arguments. This enables one-click prompt execution in Raycast with variable substitution.

Implements a decentralized curation model where community members submit prompts via GitHub Issues, maintainers review and approve submissions, and approved prompts are automatically synced to CMS and published to the web gallery. GitHub's native Issue tracking, comments, and permissions system serve as the approval workflow, with no separate admin panel required. Rejected or pending prompts remain in GitHub Issues without appearing in public collections.

Curates and optimizes prompts specifically for Google's Nano Banana Pro multimodal AI model, with metadata tagging for model-specific capabilities (e.g., image understanding, text generation, multimodal reasoning). Prompts are tested against Nano Banana Pro's API to ensure they produce high-quality outputs, and the collection includes model-specific guidance on prompt structure, token limits, and best practices. The web gallery provides one-click image generation via Nano Banana Pro API integration.

Provides a separate GitHub project (nano-banana-pro-prompts-recommend-skill) that implements an AI agent for recommending prompts based on user intent, style preferences, or subject matter. The agent is linked to the web gallery and uses semantic matching or LLM-based reasoning to suggest relevant prompts from the 10,000+ collection. Recommendations can be filtered by language, category, or user-provided context.

Implements a TypeScript i18n.ts module that handles locale-specific transformations for 16 languages, including category name translation, prompt text localization (where applicable), and language-specific formatting rules (e.g., punctuation, date formats). The pipeline reads locale configuration, applies transformations during README generation, and ensures consistency across all 16 language variants. Supports both static translations (category names) and dynamic localization (prompt metadata).

Implements a bidirectional sync mechanism (via cms-client.ts and sync-approved-to-cms.ts) that keeps Payload CMS as the authoritative source while GitHub serves as a public-facing interface and contribution channel. Approved GitHub Issues are synced to CMS via REST API, and CMS updates trigger README regeneration in GitHub. The sync pipeline includes image asset handling, metadata enrichment, and conflict resolution (CMS takes precedence).

Handles image upload, storage, and preview generation for prompts via image-uploader.ts module. Supports uploading preview images alongside prompt submissions in GitHub Issues, storing assets in Payload CMS media library, and generating locale-specific cover images (e.g., nano-banana-pro-prompts-cover-en.png, nano-banana-pro-prompts-cover-zh.png). Images are referenced in generated README files and web gallery for visual discovery.