Noo88ear commited on
Commit
ad88378
Β·
verified Β·
1 Parent(s): 9490443

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -15,8 +15,8 @@ A sophisticated AI-powered image generation system that creates high-quality mar
15
 
16
  ## Features
17
 
18
- - **AI-Powered Image Generation**: Create stunning marketing images from text prompts using Google's Imagen3 via MCP server
19
- - **Automated Quality Review**: Intelligent Gemini agent automatically reviews and refines generated images
20
  - **Marketing-Focused**: Optimized for marketing materials, social media, and promotional content
21
  - **Real-time Feedback**: Get instant quality scores and improvement suggestions
22
  - **Professional Workflow**: Streamlined process from concept to final image
@@ -74,7 +74,7 @@ A sophisticated AI-powered image generation system that creates high-quality mar
74
  β”‚Prompt β”‚ β”‚ β”‚ β”‚ Reviewer β”‚
75
  β”‚ β”‚ β”‚ β”‚ β”‚ β”‚
76
  β”‚ β”‚ β”‚ β”‚ β”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”β”‚
77
- β”‚ β”‚ β”‚ β”‚ β”‚ β”‚ Ag1: Imagen3 (via MCP) β”‚β”‚
78
  β”‚ β”‚ β”‚ β”‚ β”‚ β”‚ β”‚β”‚
79
  β”‚ β”‚ β”‚ β”‚ β”‚ β”‚ Draft Image Creation β”‚β”‚
80
  β”‚ β”‚ β”‚ β”‚ β”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜β”‚
@@ -104,7 +104,7 @@ A sophisticated AI-powered image generation system that creates high-quality mar
104
 
105
  3. **Image Generation and Drafting (Top Right)**:
106
  - **Agent 1 (Gemini) Drafter**: Receives Image Prompt, orchestrates image generation
107
- - **Imagen3 (via MCP)**: Agent 1 interacts with Imagen3 through MCP server to create initial image draft
108
 
109
  4. **Marketing Review and Refinement (Bottom Right)**:
110
  - **Agent 2 (Gemini) Marketing Reviewer**: Receives Reviewer Prompt, evaluates generated image against marketing criteria
@@ -113,11 +113,11 @@ A sophisticated AI-powered image generation system that creates high-quality mar
113
  - Final **Image Response** sent back to Gradio UI
114
 
115
  ### Summary of Flow:
116
- User provides prompts β†’ Gradio UI β†’ Agent 1 drafts image with Imagen3 β†’ Agent 2 reviews and suggests refinements β†’ Iterative refinement loop β†’ Final reviewed image β†’ User receives result
117
 
118
  ### Technology Stack
119
 
120
- - **AI Models**: Google Imagen3 (via MCP), Gemini Vision
121
  - **Framework**: Gradio (Web Interface)
122
  - **Orchestration**: Custom agent handover system
123
  - **Deployment**: Hugging Face Spaces
@@ -129,7 +129,7 @@ User provides prompts β†’ Gradio UI β†’ Agent 1 drafts image with Imagen3 β†’ Ag
129
  The system was designed with a **custom handover mechanism** instead of the A2A (Agent-to-Agent) protocol for the following reasons:
130
 
131
  1. **Simplified Architecture**: The current two-agent system (generator + reviewer) doesn't require the complexity of full A2A orchestration
132
- 2. **Direct Integration**: MCP server provides direct access to Imagen3 without needing agent-to-agent communication protocols
133
  3. **Performance Optimization**: Direct handover between agents reduces latency and eliminates protocol overhead
134
  4. **Deployment Simplicity**: Hugging Face Spaces deployment is more straightforward without A2A dependencies
135
  5. **Resource Efficiency**: Fewer moving parts means better resource utilization in the cloud environment
@@ -287,7 +287,7 @@ This project is licensed under the MIT License - see the LICENSE file for detail
287
 
288
  ## Acknowledgments
289
 
290
- - Google AI for Imagen3 and Gemini technologies
291
  - Hugging Face for the deployment platform
292
  - Gradio for the web interface framework
293
  - The open-source community for various dependencies
 
15
 
16
  ## Features
17
 
18
+ - **AI-Powered Image Generation**: Create stunning marketing images from text prompts using Google's Imagen4 via MCP server
19
+ - **Automated Quality Review**: Intelligent Gemini agent (2.5-Pro) automatically reviews and refines generated images
20
  - **Marketing-Focused**: Optimized for marketing materials, social media, and promotional content
21
  - **Real-time Feedback**: Get instant quality scores and improvement suggestions
22
  - **Professional Workflow**: Streamlined process from concept to final image
 
74
  β”‚Prompt β”‚ β”‚ β”‚ β”‚ Reviewer β”‚
75
  β”‚ β”‚ β”‚ β”‚ β”‚ β”‚
76
  β”‚ β”‚ β”‚ β”‚ β”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”β”‚
77
+ β”‚ β”‚ β”‚ β”‚ β”‚ β”‚ Ag1: Imagen4 (via MCP) β”‚β”‚
78
  β”‚ β”‚ β”‚ β”‚ β”‚ β”‚ β”‚β”‚
79
  β”‚ β”‚ β”‚ β”‚ β”‚ β”‚ Draft Image Creation β”‚β”‚
80
  β”‚ β”‚ β”‚ β”‚ β”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜β”‚
 
104
 
105
  3. **Image Generation and Drafting (Top Right)**:
106
  - **Agent 1 (Gemini) Drafter**: Receives Image Prompt, orchestrates image generation
107
+ - **Imagen3 (via MCP)**: Agent 1 interacts with Imagen4 through MCP server to create initial image draft
108
 
109
  4. **Marketing Review and Refinement (Bottom Right)**:
110
  - **Agent 2 (Gemini) Marketing Reviewer**: Receives Reviewer Prompt, evaluates generated image against marketing criteria
 
113
  - Final **Image Response** sent back to Gradio UI
114
 
115
  ### Summary of Flow:
116
+ User provides prompts β†’ Gradio UI β†’ Agent 1 drafts image with Imagen4 β†’ Agent 2 reviews and suggests refinements β†’ Iterative refinement loop β†’ Final reviewed image β†’ User receives result
117
 
118
  ### Technology Stack
119
 
120
+ - **AI Models**: Google Imagen4 (via MCP), Gemini Vision
121
  - **Framework**: Gradio (Web Interface)
122
  - **Orchestration**: Custom agent handover system
123
  - **Deployment**: Hugging Face Spaces
 
129
  The system was designed with a **custom handover mechanism** instead of the A2A (Agent-to-Agent) protocol for the following reasons:
130
 
131
  1. **Simplified Architecture**: The current two-agent system (generator + reviewer) doesn't require the complexity of full A2A orchestration
132
+ 2. **Direct Integration**: MCP server provides direct access to Imagen4 without needing agent-to-agent communication protocols
133
  3. **Performance Optimization**: Direct handover between agents reduces latency and eliminates protocol overhead
134
  4. **Deployment Simplicity**: Hugging Face Spaces deployment is more straightforward without A2A dependencies
135
  5. **Resource Efficiency**: Fewer moving parts means better resource utilization in the cloud environment
 
287
 
288
  ## Acknowledgments
289
 
290
+ - Google AI for Imagen4 and Gemini technologies
291
  - Hugging Face for the deployment platform
292
  - Gradio for the web interface framework
293
  - The open-source community for various dependencies