Морозов Андрей 2d729d92dc | ||
---|---|---|
.vscode | ||
Python310 | ||
scripts | ||
.gitignore | ||
README.md | ||
gen_mindalle.bat | ||
gen_stable_diff.bat | ||
get_dependencies.bat | ||
get_dependencies_global.bat | ||
login.bat | ||
prompt.txt | ||
rem_dependencies.bat | ||
rem_dependencies_global.bat | ||
run_all.bat |
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
-
Run "get_dependencies.bat";
- if you see connections errors, just run the script again to be shure everything is installed;
-
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
-
You are redy to go.
How to run
- Clone this repo;
- Write your promt to "promt.txt";
- Run "run_all.bat";
- First run will be slow due to downloading weights
- When amount is asked, enter any number you want;
- Quantity of output pictures = amount * 60
- Just wait. It can be a long process;
- You can find output files in .\data\out\%Timestamp% folder. Jpeg contain commentaries in metadata with some settings used while generating.
How to update
Small update
- Get new scripts from this repo;
- Run "rem_dependencies.bat";
- Run "get_dependencies.bat".
Big update
- Delete old files;
- Don't forget to save your fenerated pictures
- Clone this repo from scratch;
- Run "get_dependencies.bat".
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.