Comments (3)
Yikes!
For example, this is one using the yiffymix_v43 two days ago.
To clarify: Were you still on 3.x two days ago?
I believe this is the model: https://civitai.com/models/129996/easyfluff
Based on the description there, this model uses v-prediction. I noticed a couple issues in our handling:
- We aren't correctly determining checkpoint scheduler prediction on import, so the model is set as epsilon.
- When you go and change it to v-pred, it doesn't change the config file path, which is required to convert the model to diffusers and use it.
- Even if you manually fix the config file path, if the model was converted once before, it will not be converted again. The diffusers conversion cache must be emptied to trigger the conversion again.
Once I manually fix the config file path (stable-diffusion/v1-inference-v.yaml
is the correct value) and delete the model conversion cache, I get better images. Using CLIP Skip 2 and CFG Rescale 0.7 per the model page:
So no longer totally broken, but still not right. They all have this grainy look. I tried enabling upcast_attention
, which I think is related to v-pred and re-converting - this didn't seem to change anything.
At this point, I'm not sure how to proceed further.
@lstein Any ideas for fixing the root issue?
I think there are clear solutions for each of the 3 issues I noted:
- Figure out how to determine the prediction type from the state dict for SD1. Right now, it doesn't try, jsut defaults to epsilon. I don't know how to do this.
- Do not hardcode the ckpt config file paths unless the user explicitly sets it. When we convert, if there is no config file path, we determine the right config file using the same logic the probe uses.
- Invalidate the ckpt conversion cache if a change to a model record means it would convert differently. We could simply invalidate the conversion cache on any model config change. I think that is reasonable, though it is less efficient.
from invokeai.
I was still on 3.x two days ago, yeah. I had used an old installer I still had on my desktop at the time.
The model you're using is correct, but just to check, is that using the config file provided with the model? Not sure if that might be causing the grainy look there or if there's indeed still an issue.
from invokeai.
No, I didn't notice there was a config file provided. Unfortunately, using it doesn't change the outputs - still grainy. I made sure to re-convert the model.
In v3, we used the diffusers ckpt conversion logic with some fixes. Those fixes were upstreamed to diffusers, and in v4 we moved back to the standard diffusers conversion. I suspect we are missing an arg in the conversion calls, or maybe diffusers has a bug.
from invokeai.
Related Issues (20)
- [enhancement]: Need better Toast text for loading model defaults
- [bug]: Weird Memory Error HOT 6
- [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
- [enhancement]: CFG++ HOT 4
- [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
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.