Captured photo
Instruct pix2pix

About

This model edits images per user instructions, leveraging both GPT-3 and Stable Diffusion. It operates quickly without per-sample tuning, producing diverse edits from direct prompts.

Percs

Image editing
High resolution
Follows instructions
Multiple styles

Settings

Negative Prompt-  Type what you do not want to see in the generation
Inference Steps-  Number of denoising steps
Guidance Scale-  Prompt alignment
Scheduler