Comments (4)
The handling of tiled decode hasn't changed in some time - several months. This functionality is handled wholly by diffusers
, and it appears their implementation also hasn't changed in months.
It's possible there was some change in another area of diffusers
or invoke that indirectly affect how tiled decoding is handled.
However, slight changes like this are known effects of tiled decoding. The model doesn't have the full context of the image, it's expected that the tiled decode has measurable and sometimes visual differences. There's some discussion here, though the example images appear to be missing now.
A more convincing comparison would be between a v3.7.0 image with tiled decode vs v4 image with tiled decode (no upscaling please, that adds another variable to the equation). Ideally a few comparisons.
from invokeai.
It is less visible during the first pass, since there is typically only a single tile (2 at most if the resolution is set a bit higher). Still here are two more example without upscaling (512x768). Images 1 and 3 were generated via InvokeAI 3.7, while 2 and 4 were generated using InvokeAI 4.0.2. Same parameters for alle images.
from invokeai.
Thanks for those examples. It's still very noticeable. I think we need to test this with diffusers (i.e. via separate script, not within invoke) to confirm where the problem is.
from invokeai.
Your welcome. And thank you for looking into it!
from invokeai.
Related Issues (20)
- [bug]: Canvas pixel shift on saving an image to the gallery makes the image blurry
- [enhancement]: Model manager should find available filename HOT 1
- [bug]: Can't change the brush size with CTRL + Scroll Wheel without clicking once on the canvas after using CTRL + Tab to change tabs HOT 1
- [bug]: Control layers with weight values above 1 are not recalled
- [enhancement]: Add Seed Variations to the Linear UI HOT 1
- [enhancement]: add multiple image to canvas and moveable image on canvas
- [bug]: When recalling prompts, "style" prompts are not always recalled correctly
- [bug]: Certain SDXL controlnets fail conversion from safetensors with `KeyError: 'time_embed.0.weight'` HOT 1
- [bug]: Dimensions not properly preserved when switching models
- [enhancement]: Support SDXL Checkpoint VAEs HOT 4
- [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
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.