technicalkiwi
/
latentblending
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
Lunar Ring 2023-01-11 13:02:49 +01:00 committed by GitHub
parent e50f713479
commit 24ccb6c9a1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
README.md
View File

@ -136,7 +136,14 @@ lb.setup_branching(num_inference_steps, list_nmb_branches, list_injection_streng
## Perceptual aspects ## Perceptual aspects
With latent blending, we can create transitions that appear to defy the laws of nature, yet appear completely natural and believable. The key is to surpress processing in our [dorsal visual stream](https://en.wikipedia.org/wiki/Two-streams_hypothesis#Dorsal_stream), which is achieved by avoiding motion in the transition. Without motion, our visual system has difficulties detecting the transition, leaving viewers with the illusion of a single, continuous image. However, when motion is introduced, the visual system can detect the transition and the viewer becomes aware of the transition, leading to a jarring effect. Therefore, best results will be achieved when optimizing the transition parameters, particularly the depth of the first injection. With latent blending, we can create transitions that appear to defy the laws of nature, yet appear completely natural and believable. The key is to surpress processing in our [dorsal visual stream](https://en.wikipedia.org/wiki/Two-streams_hypothesis#Dorsal_stream), which is achieved by avoiding motion in the transition. Without motion, our visual system has difficulties detecting the transition, leaving viewers with the illusion of a single, continuous image. However, when motion is introduced, the visual system can detect the transition and the viewer becomes aware of the transition, leading to a jarring effect. Therefore, best results will be achieved when optimizing the transition parameters, particularly the depth of the first injection.
# Future work # Coming soon...
* Depth model - [ ] Huggingface / Colab
* Zooming etc. - [ ] Transitions with Depth model
- [ ] Zooming
- [ ] Iso-perceptual spacing for branches (=better transitions)
Stay tuned on twitter: ```@j_stelzer```
Contact: ```stelzer@lunar-ring.ai``` (Johannes Stelzer)