SDImageGenerator 2.0 released

Releasing  SDImageGenerator(SDIG) v2.0.0  (Text to image generation desktop app for Windows)

• Works on CPU/GPU but CPU image generation is slow(Recommended to use GPU for faster image generation)
•  The stable diffusion 1.5 model is used as the default
• Added model switching (For advanced use)
• Supports dreambooth models (checkpoint files (.ckpt) supported)
• Added textual inversion support(Hugging Face's concepts library models supported)
• Added VAE(Variational autoencoder) support for fine details
• Added CodeFormer support
• Updated full precision mode with float32
• Added high-resolution duplication fix setting
•  Image-to-image now supports k-diffusion samplers
•  Added Image-to-image mask image support 
• Added cancel functionality
• Negative prompt support, use [ ] to use negative promptE.g: a cute [white] dog
• Added Attention control support in prompt :

            Use "+" to increase attention - a house, apple++ tree

            Use "-" to decrease attention - a house, apple- tree

• Supports prompt-to-Prompt editing (Cross attention control)

              E.g:  In the below prompt cat will be replaced with a dog

                       A cat.swap(dog) riding bicycle

•  Supports prompt blending 

                E.g:  car:0.30 boat:0.70 hybrid

Download: https://rupeshsreeraman.itch.io/sdimagegenerator