Type | |
Stats | 662 |
Reviews | (110) |
Published | Feb 27, 2023 |
Base Model | |
Training | Steps: 2,000 |
Training Images | Download |
Hash | AutoV2 5EDFD56892 |
spop style
Features a wide variety: humans, creatures, outer space, forests, and landscapes in the specific style of SPOP: She-Ra and the Princesses of Power, the Dreamworks version.
This LoRA in an upgrade from the original Dreambooth checkpoint
> 🌟 Disclaimer: Most of the sample images were posed using ControlNet. It may be difficult to reproduce the sample images unless you have it. If you need help, ask!
Model Usage
Trained using kohya-ss SD scripts.
Using the Additional Networks extension within Auto1111 is recommended as you can adjust UNet and Text Encoder weights independently.
If you do not want to use this extension, you may need to use the token spopstyle in your prompts to activate the style of the LoRA.
Use any NAI or animation/cartoon type model:
Weight: 0.1 - 0.9
Clip Skip: 2
> 💥 VAE Check: Double check to make sure you're using the correct VAE per model. Having a VAE active (especially the correct one) will give you the best results.
ControlNet settings
Using ControlNet? Here are the settings used in the sample images:
Source images: any open pose rig (images attached to Model info!)
Preprocesser: None
Model: control_openpose-fp16.safetensors
Weight: 1.15
Guidance strength (T): 1
Scale to Fit: true
Width: 512
Height: 768