Comments (4)
I think this might just make it a score-based model. Like Yang Songs earlier work, or instead very like EDM. The +1
wouldn't really matter I feel.
from consistency_models.
Or is it possible to use both Loss( f(x0+t_{n+1}*z), x0 ) and Loss( f(x0+t_{n+1}*z) , f(x0+t_{n}*z) )? The first term enforces the similarity with the ground truth images, while the second term enforces the consistency. Simply using the consistency term would in fact decrease the generation performance or lead to longer training.
from consistency_models.
loss(x0+t_{n+1}*z), x0) can only enforce the model to learn the expectation of x0, not the target point of the current trajectory. It is a wrong loss term for one step diffusion
from consistency_models.
loss(x0+t_{n+1}*z), x0) can only enforce the model to learn the expectation of x0, not the target point of the current trajectory. It is a wrong loss term for one step diffusion
Yes, although you can target the GT I think this would actually make the task harder. By trying to target the trajectory you are smoothing the data manifold which makes training easier.
from consistency_models.
Related Issues (20)
- Sampling with Diffusers HOT 1
- RuntimeError in the sample `diffusers` code in README.md HOT 2
- Different batches size while training
- “multi-gpu error” dist.all_gather(gathered_samples, sample) # gather not supported with NCCL HOT 1
- where can we get the ref_batches/imagenet64.npz file for FID evaluation HOT 1
- [inpainting] wrong shape?
- Request for unconditional model on ImageNet 64*64
- GPU Training Time for CD and CT Models on ImageNet64X64?
- Why does the training not stop?
- ModuleNotFoundError: No module named 'cm' HOT 3
- Why use teacher model in Consistency training HOT 6
- Can I use the checkpoint provided by the original EDM paper to train the consistency model?
- Is there a non-stochastic sampling method? HOT 1
- Issue with `use_fp16=True` Leading to Type Conversion Error in `unet.py` HOT 1
- An module error when running cm_train.py HOT 1
- cannot import name '_get_cpp_backtrace' from 'torch._C'请问这种问题该怎样解决呢 HOT 2
- How is Consistency for Any Point on the ODE Path Achieved in the Consistency Model?
- After running, no .npz file appeared HOT 2
- the libfabric EFA provider is operating in a condition that could result in memory corruption or other system errors. HOT 11
- from flash_attn.flash_attention import FlashAttention . Where is FlashAttention?Why can't I import it? HOT 5
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 consistency_models.