Checkpoint Models & Architecture
A saved state of a trained AI model containing all its learned weights. In Stable Diffusion, checkpoints are the main model files that determine the overall style and capabilities.
A checkpoint (also called a model) is the complete trained state of an AI image generator. Different checkpoints produce vastly different results.
File Formats
- .safetensors: Modern, secure format (recommended)
- .ckpt: Legacy format, can contain executable code
Types of Checkpoints
Base Models
Official releases from model creators:
- SD 1.5 (~4GB)
- SDXL (~6.5GB)
- SD 3 (~8GB+)
Fine-tuned Models
Trained on specific content:
- Realistic (photorealistic focus)
- Anime (Japanese animation style)
- Artistic (painting, illustration)
- Specialized (architecture, products, etc.)
Popular Checkpoints
| Name | Base | Style |
|---|---|---|
| Realistic Vision | SD 1.5 | Photorealistic |
| DreamShaper | SD 1.5 | Fantasy/versatile |
| Anything V5 | SD 1.5 | Anime |
| Juggernaut XL | SDXL | Photorealistic |
| Pony Diffusion | SDXL | Stylized |
Using Checkpoints
- Download from Civitai or Hugging Face
- Place in models/checkpoints folder
- Select in your UI
- Different checkpoints may need different settings
Merging
Checkpoints can be merged to combine styles, creating new models with mixed characteristics.