Comments (2)
yea, it is easy, just add cross attention layers to T5 encoder output of the text, and then they use classifier free guidance
from phenaki-pytorch.
@lucidrains I wanna ask more detailed questions about cross attention because I am new to this. During pretrain, fixed length of video frames input to model and cross attention with text prompt tokens corresponding to the frames. But during video generation inference, prompt is different and generated frames length would be also different, I guess. Then, during inference, I do wonder how to determine the number of empty video tokens. If you know that, could you let me know it please?
Thank you😀
from phenaki-pytorch.
Related Issues (20)
- Different video sizes HOT 1
- Running out of CUDA/GPU spaces HOT 17
- Release pretrained models? HOT 6
- In phenaki to output video_codebook_ids... HOT 1
- how to run cvivit trainer or phenaki trainer HOT 8
- There is error in ema HOT 1
- model.buffer is EMPTY list in EMA get_buffers_iter function HOT 4
- I have a theoretical question about maskgit cross attention HOT 2
- ImportError: T5Tokenizer requires the SentencePiece library but it was not found in your environment. HOT 4
- What is out of index? HOT 1
- Unconditional Training returns errors HOT 5
- Einops Error. Shape mismatch HOT 2
- Compatibility issue with A100-80G with version 0.0.67 HOT 3
- discriminator loss goes to infinity HOT 12
- Problem With Multi-GPU Training HOT 2
- Where can find '/path/to/trained/cvivit.pt' HOT 1
- Successfully trained the CViViT! Working on the second step HOT 5
- Training the Phenaki - RuntimeError: CUDA error: device-side assert triggered HOT 2
- cannot reproduce HOT 7
- training data 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 phenaki-pytorch.