Try Replicate web demo here:

This is a Cog implementation of Detailed, higher-resolution images from Stable-Diffusion, originally implemented by @jquesnelle here. Additionally, safety checker is added.

txt2imghd is a port of the GOBIG mode from progrockdiffusion applied to Stable Diffusion, with Real-ESRGAN as the upscaler. It creates detailed, higher-resolution images by first generating an image from a prompt, upscaling it, and then running img2img on smaller pieces of the upscaled image, and blending the result back into the original image.

txt2imghd with default settings has the same VRAM requirements as regular Stable Diffusion, although generation of the detailed images will take longer.

Install Cog if you haven't:

1. Clone stable-diffusion git clone https://github.com/CompVis/stable-diffusion
2. Put cog.yaml and predict.py in the root directory of stable-diffusion and download weights (as noted at the top of predict.py)
3. Generate high-resolution images with cog predict --prompt <your_prompt>