Comments (1)
haoosz
commented on July 24, 2024
Hi, do you infer and get the noisy images as well when using the released trained model? I cannot identify the bug in your case. Please try the released trained model and use exactly the same inference command as readme if you haven't.
For the issue of batch size, you are right that I may use the default batch size of 1 in the code. You can just use 1 and it consistently produces good results.
from vico.
Related Issues (15)
- Multiple conditioning images
- Evaluation Code HOT 1
- init text on evaluation HOT 2
- reference image on evaluation?
- SDXL support? HOT 1
- about evaluation code
- do you plan on releasing training code? HOT 1
- Any plans for a diffusers version? HOT 8
- How about the results with human images as inputs? HOT 14
- Hardware Needs and GPU Colab? HOT 1
- need detailed tutorial to use Vico with AMD GPU on linux with Rocm HOT 1
- Image cross attention across all tokens? HOT 4
- About classifier free guidance HOT 3
- Does it support inpainting? 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 vico.