Input prompts from cli without restarting it everytime a new prompt is added #556
devingDev
started this conversation in
Feature suggestions
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hey i'd like to input prompts (with extra settings such as iter and scale and so on) via cli
my app is written in c# and what i thought is to keep the process open like it does in the webui and i pass it arguments via standard input (?)
this is because the startup takes so much time every time i want a new prompt..
so for example it would just wait for user input and use that
either directly like we use in txt2img.py or via yaml config whichever is nicer (or both?)
The part I'm talking about is this:
(ldm) C:\SD>python scripts/webui.py --cli txt2img.yaml Loaded GFPGAN Loaded RealESRGAN with model RealESRGAN_x4plus Loading model from models/ldm/stable-diffusion-v1/model.ckpt Global Step: 470000 LatentDiffusion: Running in eps-prediction mode DiffusionWrapper has 859.52 M params. making attention of type 'vanilla' with 512 in_channels Working with z of shape (1, 4, 32, 32) = 4096 dimensions. making attention of type 'vanilla' with 512 in_channels
Just found this not sure if it was the same request as that?
Edit:
Originally posted by @tommyfive5 in #541
Beta Was this translation helpful? Give feedback.
All reactions