Comments (4)
they are models trained a bit longer. and some problems in datasets are fixed (for example, our previous dataset included too many greyscale human images making controlnet 1.0 tends to predict greyscale images).
the difference between controlnet 1.0 and 1.1 is in some way similar to the difference between SD 1.2 and 1.4
from controlnet-v1-1-nightly.
I have been experiencing issues with face quality when using controlnet. Probably similar to this topic: Mikubill/sd-webui-controlnet#232
Can we expect changed behavior in that regard with the new models?
(Or isn't this a model-related issue in the first place?)
from controlnet-v1-1-nightly.
Also curious about what was the enabler to improve the models :)
from controlnet-v1-1-nightly.
they are models trained a bit longer. and some problems in datasets are fixed (for example, our previous dataset included too many greyscale human images making controlnet 1.0 tends to predict greyscale images). the difference between controlnet 1.0 and 1.1 is in some way similar to the difference between SD 1.2 and 1.4
Thanks for your reply and nice contribution.
from controlnet-v1-1-nightly.
Related Issues (20)
- How to train semantic-segmentation-controlnet with my data HOT 1
- Is there any plan to support ***comfyUI***? HOT 3
- [Request] Please enable/restore PNG info "send to" functionality ASAP
- Inpaint + Lama Preprocessor
- inpainit effect between the stable diffusion and controlnet
- Failure to render DWPOSE properly
- Error: Images generated but CN not working, even when enable checked
- ColorGrading / Preset Controlnet?
- ControlNet更新到2023年9月5日版本后,使用Tile模型结合Tiled Diffusion & VAE报错 HOT 1
- RuntimeError: mat1 and mat2 shapes cannot be multiplied (154x2048 and 768x320) HOT 2
- Upgrade to the latest version, WEBUI load controlnet error HOT 1
- Question : openpose preprocessor
- ControlNet Tile is missing the files `fp16.bin` `fp16.safetensors` and `safetensors` HOT 4
- Running on CLI
- Connection errored out. HOT 1
- cost time HOT 1
- Training Details for tile model HOT 3
- Can I use SDXL for training, such as I want to train inpaints HOT 3
- question in depth preprocess
- Can I ask how you trained the IP2P model? HOT 4
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 controlnet-v1-1-nightly.