Create pictures with Mindalle and stable diffusion. Python script with dependencies installation bat file.
Go to file
Морозов Андрей 21c9ae8a8d Preparations for diffusers update 2022-10-09 15:41:45 +04:00
.vscode Preparations for diffusers update 2022-10-09 15:41:45 +04:00
Python39 Preparations for diffusers update 2022-10-09 15:41:45 +04:00
scripts Support for 6gb cards 2022-09-24 12:03:40 +04:00
.gitignore Added more libs 2022-09-17 16:34:37 +04:00
README.md can run on 4gb cards 2022-09-24 09:47:40 +00:00
gen_mindalle.bat Disabled nsfw filter and updated some scripts 2022-09-20 12:40:25 +04:00
gen_stable_diff.bat Disabled nsfw filter and updated some scripts 2022-09-20 12:40:25 +04:00
get_dependencies.bat Disabled nsfw filter and updated some scripts 2022-09-20 12:40:25 +04:00
login.bat Disabled nsfw filter and updated some scripts 2022-09-20 12:40:25 +04:00
prompt.txt Disabled nsfw filter and updated some scripts 2022-09-20 12:40:25 +04:00
rem_dependencies.bat Added libs ti python 2022-09-17 16:26:13 +04:00
rem_dependencies_global.bat Preparations for diffusers update 2022-10-09 15:41:45 +04:00
run_all.bat Disabled nsfw filter and updated some scripts 2022-09-20 12:40:25 +04:00

README.md

MinDalle_StableDiff

Create pictures with Mindalle and stable diffusion. Python script with dependencies installation bat file.

How to set up dalle mini + stable diffusion:

  1. Run "get_dependencies.bat"
    • if you see connections errors, just run the script again to be shure everything is installed.
  2. Run "login.bat" to login to your HuggingFace profile. a. Go to https://huggingface.co/CompVis/stable-diffusion-v1-4 and make sure to accept the terms. b. Go to Your Profile > Settings > Access Tokens c. Create a write token/Copy an existing Token key and enter in the cmd window.
    • It can be done once and forever untill you delete token from C:\Users\%YOUR_USERNAME%\.huggingface
  3. You are redy to go.

How to run

  1. Write your promt to "promt.txt"
  2. Run "run_all.bat"
    • First run will be slow due to downloading weights.
  3. When amount is asked, enter any number you want.
    • Quantity of output pictures = amount * 60
  4. Just wait. It can be a long process.
  5. You can find output files in .\data\out\%Timestamp% folder. Jpeg contain commentaries in metadata with some settings used while generating.

Requirements

  • 10GB of free space.
  • Nvidia card with 4GB+ video memory.

Tests

  • RTX3070: 12 - 14 seconds per picture.
  • RTX2060_Laptop: 21 - 25 seconds per picture.