image2-ads-studio
Health Uyari
- License — License: Apache-2.0
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Low visibility — Only 8 GitHub stars
Code Uyari
- process.env — Environment variable access in apps/ad-image-agent/server/llm-server.mjs
- network request — Outbound network request in apps/ad-image-agent/server/llm-server.mjs
- network request — Outbound network request in apps/ad-image-agent/src/App.tsx
Permissions Gecti
- Permissions — No dangerous permissions requested
This tool is an advertising prompt agent that transforms business briefs and reference images into debranded, production-ready image prompts for advertising production. It acts as an automated pipeline that parses intent, retrieves templates, and uses an LLM to generate optimized outputs.
Security Assessment
The tool does not request dangerous system permissions and no hardcoded secrets were detected. However, it does make outbound network requests and accesses environment variables, primarily within the server module and frontend application. This is standard behavior for an LLM-powered agent that needs to communicate with external AI APIs, but it does mean your prompts and briefs will be sent to third-party language models. Overall risk is rated as Low.
Quality Assessment
The repository is actively maintained with a very recent last push. It uses the permissive Apache-2.0 license, making it safe for commercial and private use. The documentation is thorough, clearly explaining the pipeline and providing examples. However, community trust and visibility are currently very low, as the project has only 8 GitHub stars. As a relatively new and untested tool, it has not yet been widely vetted by the open-source community.
Verdict
Safe to use, but be aware that business briefs are transmitted externally to LLM APIs and the project currently lacks extensive community vetting.
Advertising prompt agent for Image2: turns business briefs and reference images into debranded, production-ready image prompts.
Image2 Ads Studio
Advertising prompt agent for Image2: turn business briefs and reference images into debranded, production-ready image prompts.
This is not another prompt dump. Prompt libraries are useful for browsing examples; Image2 Ads Studio is a working prompt pipeline for advertising production. It parses a customer brief, retrieves advertising templates and visual recipes, rewrites references through an LLM prompt brain, validates deterministic execution details, and returns an optimized prompt that can be manually tested in Image2.
This repository is the Community Edition. It opens the agent framework, local Web workbench, all current 220 business templates, 240 visual recipes, LLM prompt brain interface, deterministic prompt checks, reference image policy, and a public case gallery.
Why This Is Different
Most Image2 prompt repositories answer: "What prompt can I copy?"
Image2 Ads Studio answers: "Given this business brief, copywriting, industry, aspect ratio, and reference image, what prompt should the agent produce?"
| Prompt libraries | Image2 Ads Studio |
|---|---|
| Curated examples for inspiration | Runnable advertising prompt agent |
| Start from existing prompts | Start from customer brief and reference images |
| General creative coverage | Advertising vertical: storefronts, posters, ecommerce, product ads, signage, brand walls, commercial photography |
| Prompt text is the product | Parser, retriever, compiler, LLM rewrite, deterministic checks, and JSON records are the product |
| Usually copy/paste driven | Produces parsed intent, matched templates, visual recipes, design plan, optimized prompt, and source policy |
| References may stay close to source | Public gallery prompts are regenerated, debranded, attributed, and made reusable |
| Hard to connect to business systems | Designed for later ERP fields, template governance, adapters, and production workflows |
Prompt Gallery
The public gallery contains 100 image-to-prompt cases from project-generated concepts and multiple in-repo source libraries. Each case includes one preview image, one Image2-ready optimized prompt, source attribution, and an in-repo composite source made from matched advertising templates plus visual recipes.
View the full gallery: examples/gallery/cases.md
| Preview | Optimized Prompt Excerpt |
|---|---|
![]() |
Beverage Product Ad ConceptCreate a commercially usable 16:9 beverage advertising hero image for a new debranded sparkling drink. Composition: place a tall matte-gloss red can slightly right of center... |
![]() |
Premium Appliance Product Ad ConceptCreate a 16:9 premium consumer-electronics product advertising hero image for a debranded high-end airflow appliance. Use a black-and-champagne-gold cylindrical device... |
![]() |
Luxury Amber Perfume AdCreate a square 1:1 luxury beauty product advertisement for a debranded amber perfume bottle. Show one classic rectangular glass bottle as the hero object... |
![]() |
Tropical Citrus Soda Ad PosterCreate a 9:16 vertical commercial beverage poster for a tropical citrus soda campaign. Show one large transparent plastic bottle as the hero object... |
![]() |
Moss Radio Brand Identity Showcase BoardCreate a square 1:1 brand-identity showcase board for a fictional audio, retail, or culture-focused business. Build a dense editorial presentation... |
![]() |
Zoo Visitor Wayfinding MapCreate a polished 16:9 advertising-style wayfinding map board for a fictional wildlife park campaign, designed as a commercially usable tourism graphic... |
![]() |
E-Commerce Product Detail Page LayoutCreate a 9:16 vertical e-commerce product detail poster for a futuristic consumer electronics hero product. Use a dense marketplace layout... |
Source and license notes are tracked in gallery attribution. The gallery is not a copied prompt collection: upstream prompts/images are used as structure references, then this project regenerates, debrands, and normalizes the final prompt through the same agent flow used by the Web workbench.
Why It Exists
General image-generation prompts are unstable for advertising production. A local shop owner may say "make a milk tea storefront signboard", but production-ready output needs structure: task type, industry, copywriting, aspect ratio, material constraints, reference image policy, and clear composition.
Image2 Ads Studio turns that loose brief into a structured advertising plan and an optimized prompt that can be manually tested in Image2 or another image-generation tool.
Core Features
- Advertising vertical coverage: storefront signboards, posters, roll-up banners, event backdrops, wayfinding signage, brand walls, local promotions, ecommerce main images, product ads, and commercial photography.
- Open template library: 220 business templates and 240 visual recipes.
- LLM prompt brain: uses a Responses-compatible LLM endpoint to refine the rule prompt.
- Reference image policy: user uploads can be read by the LLM and marked for later Image2 editing; upstream references are only used for visual understanding.
- Deterministic prompt validation: removes vague expressions and requires composition, lighting, typography, material, and image-reference policy.
- Local Web UI: prompt workbench with brief input, optimized prompt output, preview placeholder, and retrieval signals.
Quick Start
pnpm install
pnpm --filter ad-image-agent-core test
pnpm --filter ad-image-agent build
export OPENAI_API_KEY="your_api_key"
pnpm --filter ad-image-agent serve:llm
Open:
http://127.0.0.1:5174
The app does not call an image-generation API in this edition. Copy the optimized prompt into your image-generation tool and upload user reference images when the app marks them for Image2 participation.
Architecture
flowchart LR
A[User Brief] --> B[Intent Parser]
B --> C[Template Retriever]
C --> D[Visual Recipe Retriever]
D --> E[LLM Prompt Brain]
E --> F[Optimized Prompt]
F --> G[Image2 Manual Test]
G --> H[Case Library]
H -. Template / Recipe Update .-> C
H -. Template / Recipe Update .-> D
Community vs Commercial
| Capability | Community Edition | Commercial Edition |
|---|---|---|
| Local Web UI | Included | Included |
| Core prompt agent framework | Included | Included |
| Business templates | 220 open templates | Custom/private templates and governance |
| Visual recipes | 240 open recipes | Custom/private recipes and scored evaluation |
| LLM prompt brain | Interface + local server | Production setup |
| Image generation | Manual adapter | Real adapters and storage |
| ERP integration | Overview docs | Connectors, field mapping, deployment |
| Case gallery | Public samples | Private scored case library |
Commercial work can add ERP connectors, real image-generation adapters, deployment support, custom private templates, and production case evaluation.
Repository Layout
apps/ad-image-agent Local Web workbench
packages/ad-image-agent-core Parser, retrievers, compiler, adapters, tests
examples Sample briefs and generated records
docs Architecture, adapter, ERP, authoring, roadmap
scripts Community validation and asset counting
Development
pnpm --filter ad-image-agent-core test
pnpm --filter ad-image-agent-core build
pnpm --filter ad-image-agent typecheck
pnpm --filter ad-image-agent build
License
Apache-2.0. See LICENSE.
Yorumlar (0)
Yorum birakmak icin giris yap.
Yorum birakSonuc bulunamadi






