AI Image Generation
VariantLab supports multiple AI models from different providers for image generation. Choose the model that best fits your needs based on quality, speed, resolution, and style.
Available Models
Gemini 2.5 Flash Image
Google's fast, cost-effective image generation model. Great for rapid iteration and exploring prompt ideas.
| Specification | Value |
|---|---|
| Provider | |
| Max Resolution | 1024px |
| Speed | Fast (seconds) |
| Aspect Ratios | 10 options |
Best for: Prototyping, testing prompts, high-volume generation, budget-conscious projects.
Gemini 3.0 Pro Image
Google's high-quality generation model with support for up to 4K resolution.
| Specification | Value |
|---|---|
| Provider | |
| Max Resolution | 4096px |
| Speed | Slower (10-30 seconds) |
| Size Options | 1K, 2K, 4K |
| Aspect Ratios | 10 options |
Best for: Final production images, print-quality output, projects requiring high resolution and detail.
FLUX.2 [pro]
High-fidelity image generation from Black Forest Labs with a commercial license.
| Specification | Value |
|---|---|
| Provider | Black Forest Labs |
| Max Resolution | 2048px |
| Speed | Moderate |
| Size Options | 1K, 2K |
| Aspect Ratios | 10 options |
Best for: Commercial projects, photorealistic styles, high-quality generation with licensing clarity.
FLUX.2 [pro] is generation-only. Variations use FLUX.2 [pro] Edit automatically.
GPT Image 1
OpenAI's multimodal image generation model with quality level control.
| Specification | Value |
|---|---|
| Provider | OpenAI |
| Max Resolution | 1024px |
| Speed | Moderate |
| Quality Levels | Low, Medium, High |
| Aspect Ratios | 3 options (1:1, 2:3, 3:2) |
Best for: Diverse art styles, text rendering in images, OpenAI ecosystem integration.
GPT Image 1.5
OpenAI's latest image model — more cost-effective with an additional "auto" quality option.
| Specification | Value |
|---|---|
| Provider | OpenAI |
| Max Resolution | 1024px |
| Speed | Moderate |
| Quality Levels | Low, Medium, High, Auto |
| Aspect Ratios | 3 options (1:1, 2:3, 3:2) |
Best for: Cost-effective OpenAI generation, letting the model choose optimal quality with "auto" mode.
Imagen 4
Google's latest dedicated image generation model with excellent prompt adherence.
| Specification | Value |
|---|---|
| Provider | |
| Max Resolution | 2048px |
| Speed | Moderate |
| Size Options | 1K, 2K |
| Aspect Ratios | 5 options |
Best for: High-quality generation, photorealistic output, strong prompt following.
Imagen 4 is generation-only. Variations automatically use a compatible Gemini model.
Imagen 4 Ultra
The highest-quality Imagen model with enhanced detail and output quality.
| Specification | Value |
|---|---|
| Provider | |
| Max Resolution | 2048px |
| Speed | Slower |
| Size Options | 1K, 2K |
| Aspect Ratios | 5 options |
Best for: Maximum quality output, detailed illustrations, premium production images.
Imagen 4 Ultra is generation-only. Variations automatically use a compatible Gemini model.
Seedream 4.5
ByteDance's unified generation and editing model.
| Specification | Value |
|---|---|
| Provider | ByteDance |
| Max Resolution | 2048px |
| Speed | Moderate |
| Size Options | 1K, 2K |
| Aspect Ratios | 7 options |
Best for: Generation and editing in one model, diverse art styles.
Seedream 4.5 is not yet available. It will be enabled in a future update.
Quality Levels
GPT Image models support quality levels that control output fidelity:
| Level | Description |
|---|---|
| Low | Fastest, lowest cost |
| Medium | Balanced quality and cost |
| High | Best quality, highest cost |
| Auto | Model chooses optimal quality (GPT Image 1.5 only) |
Higher quality levels produce more detailed images but cost more Mana.
Variation Model Override
Some models (like Imagen and FLUX.2 [pro]) are generation-only and don't support image editing natively. When you use these models for base generation, VariantLab automatically assigns a compatible model for variations:
| Generation Model | Variation Model |
|---|---|
| FLUX.2 [pro] | FLUX.2 [pro] Edit |
| Imagen 4 | Gemini 2.5 Flash Image |
| Imagen 4 Ultra | Gemini 2.5 Flash Image |
You can change the variation model in project settings if you prefer a different option.
Aspect Ratios
Available aspect ratios vary by model. Most models support 10 ratios:
| Ratio | Use Case |
|---|---|
| 1:1 | Avatars, icons, square art |
| 3:2 | Landscape photography |
| 2:3 | Portrait photography |
| 4:3 | Traditional landscape |
| 3:4 | Traditional portrait |
| 5:4 | Wide traditional |
| 4:5 | Tall traditional |
| 16:9 | Widescreen, banners |
| 9:16 | Vertical, mobile |
| 21:9 | Ultra-wide, panoramic |
GPT Image models support 3 ratios (1:1, 2:3, 3:2). Imagen models support 5 ratios (1:1, 3:4, 4:3, 9:16, 16:9).
Writing Effective Prompts
Structure
A good prompt includes:
- Subject - What you're generating
- Style - Art style, medium
- Details - Colors, features, accessories
- Composition - Position, framing
- Background - Setting, context
Example Prompts
Character avatar:
A cute robot mascot with large expressive blue eyes,
shiny silver metallic body, small antenna on top,
flat digital art style, centered composition,
solid white background, full body visible
Game asset:
Medieval fantasy sword with glowing blue blade,
ornate golden hilt with gems, magical particles,
game asset style, centered, transparent background,
high detail, no shadows
NFT art:
Abstract geometric lion portrait, low poly style,
vibrant gradient colors purple to orange,
modern digital art, centered, dark background
Tips for Better Results
- Be specific - "glowing blue LED eyes" beats "blue eyes"
- Include style - Always mention the art style
- Request centering - Helps with trait detection later
- Solid backgrounds - Easier for background removal
- Mention what to avoid - "no text, no watermarks"
Generation Settings
Remove Background
Enable to automatically remove the background after generation:
- Uses selected background removal model
- Replaces background with transparency
- Can be applied/removed later
Background Removal Models
| Model | Best For |
|---|---|
| U2Net Fast | General purpose, quick |
| ISNet General | Digital art, clip art |
| U2Net Pro | High quality general |
| U2Net Cloth | Clothing items |
| U2Net Human | People, portraits |
| Silueta | High quality general |
| ISNet Anime | Anime, manga style |
Cost Estimation
Before generating, the button shows the estimated Mana cost for your current model and settings. Costs vary by model, image size, and quality level — faster models and smaller sizes cost less, while higher-quality models and larger outputs cost more.
Regenerating Images
Click the regenerate icon to create a new image:
- Uses current prompt and settings
- Replaces the existing image in that slot
- Same Mana cost as new generation
Multiple Base Images
Generate up to 5 base images per project:
- Click + in the thumbnail stack
- Generate or upload into the new slot
- Star your favorite as the base for the pipeline
Having multiple options lets you pick the best starting point for your collection.