stable-diffusion-high-resolution

Make your vision a reality by turning prompts into high resolution artworks made with Stable Diffusion. Transferring ideas from your mind to digital representations has never been easier.

Hold: 0

Required: 10,000 $wRAI

58.5k runs

Input

Promt

The prompt to render.

ori_width

Width of original stable-diffusion output image. Final output will double the width. Note that 1024x1024 may run out of memory, if so, please lower the width or height.

ori_height

Height of original stable-diffusion output image. Final output will double the height. Note that 1024x1024 may run out of memory, if so, please lower the width or height.

scale

Unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty)).

steps

Number of sampling steps.

seed

The seed (for reproducible sampling).

Hold at least 10,000 wRAI to use this model

Multi AI platform is completely free, but most models are only accessible to wRAI token holders. If you have any questions, feel free to ask in our Telegram chat

Output

Download

Input

seed

662152

scale

steps

prompt

concept art of a past city, key visual, candles night, highly detailed, digital painting, artstation, concept art, sharp focus

ori_width

512

ori_height

512

Output

Download

Input

seed

70335

scale

steps

prompt

House on the seaside, key visual, candles night, highly detailed, digital painting, artstation, concept art, sharp focus

ori_width

512

ori_height

512

Output

Download

Readme

This is a Cog implementation of Detailed, higher-resolution images from Stable-Diffusion, originally implemented by @jquesnelle at https://github.com/jquesnelle/txt2imghd/blob/master/txt2imghd.py Safety checker is added additionally.

This model 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.

Сортировать по: