AI Image Generation
Create stunning images for your content using multiple AI models including Gemini Flash and Pro with aspect ratio and style controls.
AI Image Generation Overview
Audenci offers AI-powered image generation using state-of-the-art models from Google (Gemini) via fal.ai. Generate images from text prompts for social posts, blog headers, ads, and more.
Available AI Models
- Gemini 2.5 Flash Image (4 credits) - Fast, high-quality generation
- Gemini 2.5 Flash Image Edit (3 credits) - Image-to-image variations
- Gemini 3 Pro Image (12 credits) - Highest quality, most detailed
- Gemini 2.5 Flash via Vertex AI (3 credits) - Alternative endpoint
Use Flash models for most content. Reserve Pro model for hero images, ads, or high-visibility content where quality is critical.
Generating Images
Generate images from the post editor, content wizards, or Media Library. Enter a text prompt describing the image you want, select aspect ratio and model, then click Generate.
- Click 'Generate Image' from post editor or Media Library
- Enter detailed prompt describing your desired image
- Select aspect ratio (1:1, 16:9, 9:16, 4:5, etc.)
- Choose AI model (Flash or Pro)
- Set number of variations (1-4)
- Click 'Generate' - images appear in 10-30 seconds
Writing Effective Prompts
Good prompts are specific, descriptive, and include: Subject (what), Style (artistic style, mood), Composition (layout, perspective), Colors (color palette, lighting), Details (textures, atmosphere).
Example: 'A vibrant summer beach scene at sunset, warm orange and pink sky, palm trees silhouette, tropical vacation atmosphere, professional photography style, 4K quality'.
Aspect Ratios
Choose the right aspect ratio for your platform: 1:1 (Square - Instagram feed, Facebook), 16:9 (Landscape - YouTube, LinkedIn, blogs), 9:16 (Vertical - Instagram Stories, TikTok, Reels), 4:5 (Portrait - Instagram feed), 2:3 (Tall - Pinterest).
Batch Generation
Generate multiple variations at once (n parameter 1-4) to see different interpretations of your prompt. Each variation costs credits, so n=4 with Flash model costs 16 credits total.
Image-to-Image Editing
Use Edit mode (3 credits) to create variations of existing images. Upload a base image and describe changes you want. The AI preserves the composition while applying your modifications.
Edit mode is perfect for: Changing colors, Adjusting style, Adding or removing elements, Trying different moods or lighting.
Output Formats
Generated images are saved as PNG (high quality, lossless) or JPEG (smaller file size, lossy compression). PNG is recommended for images with text or sharp edges. JPEG works well for photos.
Media Storage
All generated images are automatically saved to your Media Library and GeneratedMedia database table. They're linked to the generating user, brand, and organization for easy filtering and reuse.
Credit Costs & Pro Mode
Standard Flash model costs 4 credits per image. Pro Mode (Gemini 3 Pro) costs 12 credits but provides higher quality, better detail, and more accurate prompt following. Use Pro Mode for important, high-visibility content.
Best Practices
- Be specific and descriptive in prompts
- Include style keywords (photorealistic, illustration, watercolor, etc.)
- Specify mood and atmosphere
- Use negative prompts to exclude unwanted elements
- Generate multiple variations and select the best
- Edit and refine using image-to-image mode
- Save successful prompts for future reuse