What is AI Image Generation?
AI Image Generation lets you create high-quality visuals directly within Chatly. You can generate new images or edit existing ones using different image models, all through a simple conversational experience.
Available Models
Ideogram 3.0 (Default generation model)
Nano Banana (Default editing model — also supports generation)
Nano Banana Pro (Generation model - also supports editing)
Seedream 4.0 (Generation model - also supports editing)
FluxKontext Pro (Image Editing model)
Minimax Image (Generation only)
Qwen Image Edit (Image Editing Model)
Qwen Image (Generation Only)
Out of 8 total models, 3 support both editing and generation.
Key Capabilities
Chatly’s conversational AI image generation feature supports:
Image Generation: Create new images from text prompts.
Image Editing: Edit your own images.
Reference Images: Attach up to 2 reference images per request for better results.
Aspect Ratios: Control image dimensions per model: 1:1, 3:4, 4:3, 16:9, 9:16.
Conversational Workflow: Refine results by chatting naturally with the image agent.
Variations: Each generation produces 2 images for easy comparison.
Enhancement Tools: Upscale and Background Removal (additional token costs).
Token Usage
Token consumption depends on the model used
Each request generates 2 images → tokens per image × 2
Example: If one image = 20 tokens, the request = 40 tokens
Token Consumption by Model
Model
Tokens per image
Tokens per request (2 images)
Seedream 4.0
23
46
Nano Banana
23
46
Nano Banana Pro
75
150
FluxKontext Pro
24
48
Qwen Image Edit
36
72
Qwen Image
24
46
Minimax Image
6
12
Ideogram 3.0
36
72
Token Consumption for Enhancements
Enhancement
Token Deduction / per image
Notes
Upscale
20 tokens
Applies to a single image, improves resolution.
Background Removal
1 token
Applies to a single image, removes background.
You get 100 tokens FREE on signup for image generation. 🎉
Last updated
Was this helpful?