Comments (4)
Hi,
For the panorama generation, there are actually 8 overlapping crops.
Feel free to provide more information as to what you're trying and I'll try to help.
from multidiffusion.
Hm... I think your reply is a bit different from what I'm asking.
If you put many overlapping masks directly on top of each other, for example if there were 8 crops each being the entire latent space, would it still produce a non-blurry image?
The overlapping crops you refer to only overlap in some regions:
+----+---+----+
| A |A&B| B |
+----+---+----+
But what I'm asking about is if you have something like:
+----+---+----+
| A&B&C&D&... |
+----+---+----+
Will that region be blurred?
As you're minimizing a loss within a least squared sense, how can it maintain a sharp output?
I'm also curious whether you tried this on non-latent space diffusion models such as Deep-Floyd IF, and whether the same effect was observed?
from multidiffusion.
Note that the averaging is done during the generation process, essentially averaging incremental diffusion updates. Intuitively, the model converges to a path under which the distance of each denoising direction from the average becomes very small (i.e., all constraints are satisfied).
In case the different denoising suggestions pull to extremely different directions across the entire generation, the quality of the result should be affected accordingly. However, in the applications we considered, this assumption on the ability of the model to converge to a meaningful denoising trajectory empirically hold.
I tried to run a panorama generation on the Deep-Floyd model and the results were similar to SD, but this model requires heavy memory resources for using all cascaded model, which was limiting.
from multidiffusion.
alright, that makes sense, thank you!
I see, I've been experimenting only with SD, and if it does work with DF then maybe I should try that
from multidiffusion.
Related Issues (20)
- get_views returns negative indices for values less than 512 HOT 1
- spatial controls Runtime Error
- A small problem in the diffusers. HOT 1
- When will codes for region-based generation release? HOT 8
- Bad results on the region-based demo HOT 2
- Bug in vae_optimize.py, vae_tile_forward uses 'result' when result is None HOT 1
- is this repository being maintained?
- Resolution or Projection Question about MultiDiffusion
- The evaluation dataset about COCO dataset HOT 1
- Why is averaging over overlapping regions necessary? HOT 1
- What does FTD stand for? HOT 1
- Ablation to Scheduler/Guidance Scale?
- When will codes about how to train the ckpt release?
- FoV of generated Panorama
- region based not working for multiple prompts HOT 3
- Problem of Formula Derivation HOT 1
- Equation 4 interpetation for the panorama use case HOT 1
- Bootstrapping implementation HOT 1
- Only able to generate part of the panorama 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 multidiffusion.