Comments (2)
The threshold values you are referring to aren't actually part of the generation. They are a pre-processing of the input control image. They are not saved to the metadata and I don't anticipate saving them.
What is saved to the metadata is the reference to the processed control image. This is what is actually used during generation. When I follow your steps, I do get exactly the same image after using recall all.
I think there's something missing from your steps to reproduce. Perhaps a different piece of metadata isn't recorded.
But - even if the metadata is perfectly saved and recalled and used, recreated a previous generation is best-effort only. We cannot guarantee reproducibility for image generation. Why not?
- Changes to dependencies (e.g.
torch
,diffusers
- things we use, but don't maintain) may mean generating again with the exact same settings yields a different image. - A bugfix can drastically alter image outputs.
- Changes to how settings are handled from version to version may drastically alter image outputs.
from invokeai.
With the v4.2.0 release, control adapters have been reworked and the full state of a control layer (including the processor config) is persisted/recalled to/from metadata.
from invokeai.
Related Issues (20)
- [bug]: Weird Memory Error HOT 7
- [enhancement]: Update re-downloads Pytorch and others every time HOT 3
- [bug]: Older metadata not loading control layer
- [enhancement]: Add support empty LoRA Collect HOT 1
- [bug]: Unable to connect via LAN HOT 1
- [bug]: Import error
- [enhancement]: add straight line to brush canvas
- [enhancement]: Update documentation on Infill & Scaling
- Error encountered upon updating to version 4.2.4: XL models fail to execute. HOT 2
- [enhancement]: Inpainting node HOT 1
- [enhancement]: Stable Diffusion 3 HOT 2
- Error while trying to use regional guidance with IPAdapter
- [bug]: Stable diffusion 3 install Unauthorized error, but I have setup huggingface token and accepted sd3 licience HOT 2
- [bug]: Converting checkpoint to diffusers fails HOT 4
- [enhancement]: CFG++ HOT 6
- [bug]: Pasting paths with quotes into Model Manager gives an error
- [bug]: Old broken scripts not removed when updating/installing
- [enhancement]: Improve python error message during installation
- [bug]: Deleted compare image sticks around
- [enhancement]: Copy description from Starter Models tab into models table HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from invokeai.