score_sde
score_sde_pytorch
Our great sponsors
score_sde | score_sde_pytorch | |
---|---|---|
6 | 4 | |
1,242 | 1,401 | |
- | - | |
0.0 | 0.0 | |
over 1 year ago | over 1 year ago | |
Jupyter Notebook | Jupyter Notebook | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
score_sde
- Ask HN: How to get back into AI?
-
[D] Variance of sampling in diffusion models
Perhaps the ODE interpretation would be helpful (see here and here) which turns DDPMs into neural ODEs using the Fokker-Planck equation so after the initial starting noise, the sampling process is deterministic. If samples are noisy even with the full number of steps then you might need to increase the number of steps further.
-
[D] Why is the diffution model so powerful? but the math behind it is so simple.
Turns out that diffusion models also define a certain differential equation, making it a neural ODE. Then you can just integrate the ODE in the other direction to get the exact inverse for the DDPM (it's not entirely exact b/c of numerical error in the solver, but close enough)
- [D] Are DDPMs a variation on Score Based Generative Modeling? Or is there a fundemental difference between the two?
-
Diffusion Models Beat GANs on Image Synthesis
This new approach to generative modelling looks very intriguing.
In a similar ilk, there's this ICLR paper from this year using stochastic differential equations for generative modelling: https://arxiv.org/abs/2011.13456
- [D] Efficient, concurrent input pipelines in JAX?
score_sde_pytorch
-
[D] score based vs. Diffusion models
there's an implementation of score-based models from the paper that showed how score based models and diffusion models are the same here: https://github.com/yang-song/score_sde_pytorch
-
Machine learning and black box numerical solver[D]
Someone has already mentioned Neural Ordinary Differential Equations, which is also the first thing that came to mind. There are also extensions to it, where one can use PDEs(Neural Hamiltonian Flows) or even stochastic DEs(Score-Based Generative Models) in the model. All of them covering different but overlapping use cases.
-
[Discussion] Could someone explain the math behind the number of distinct images that can be generated with a latent diffusion model?
I was considering an unconditional latent diffusion model, but for conditional models, the computation becomes much more complex (we might have to use bayes here). If we use Score-Based Generative Modeling (https://arxiv.org/abs/2011.13456), we could try to find and count all the unique local minima and saddle points, but it is not clear how we can do this...
-
[D] Machine Learning - WAYR (What Are You Reading) - Week 138
You can find an implementation here: https://github.com/yang-song/score_sde_pytorch/blob/main/models/ddpm.py
What are some alternatives?
guided-diffusion
dpm-solver - Official code for "DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps" (Neurips 2022 Oral)
pytorch-generative - Easy generative modeling in PyTorch.
Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch - [ECCV 2022] Compositional Generation using Diffusion Models
SDE - Example codes for the book Applied Stochastic Differential Equations
diffusion_models - Minimal standalone example of diffusion model
Financial-Models-Numerical-Methods - Collection of notebooks about quantitative finance, with interactive python code.
Magic123 - [ICLR24] Official PyTorch Implementation of Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
Self-Attention-Guidance - Official implementation of the paper "Improving Sample Quality of Diffusion Models Using Self-Attention Guidance" (ICCV 2023)
best-of-ml-python - 🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
DiffusionFastForward - DiffusionFastForward: a free course and experimental framework for diffusion-based generative models