DiffusionFastForward
dino-diffusion
DiffusionFastForward | dino-diffusion | |
---|---|---|
3 | 2 | |
506 | 127 | |
- | - | |
4.4 | 10.0 | |
11 months ago | over 1 year ago | |
Jupyter Notebook | Jupyter Notebook | |
MIT License | MIT License |
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.
DiffusionFastForward
-
Using Stable Diffusion's training method for Reverse engineering?
I can recommend this open-source course I made for understanding the details of denoising diffusion for images https://github.com/mikonvergence/DiffusionFastForward
- [R] Training Small Diffusion Model
- [P] A minimal framework for image diffusion (including high-resolution)
dino-diffusion
-
[R] Training Small Diffusion Model
I posted tiny standalone code for 64x64 diffusion model training here: https://github.com/madebyollin/dino-diffusion - though it doesn't have text conditioning.
-
[D] What ML or ML-powered projects are you currently building?
I made a tiny diffusion model + upsampler that runs in a webpage and generates okay images (for a super easy dataset), but the sample quality I'm getting on harder datasets is still unsatisfactory. so this weekend I'm trying to find a scaled-up model config that will generate nice images even on the harder datasets.
What are some alternatives?
Self-Attention-Guidance - Official implementation of the paper "Improving Sample Quality of Diffusion Models Using Self-Attention Guidance" (ICCV 2023)
mbot-vision - Let your Makeblock robot see using an ESP32, camera and PyTorch
score_sde_pytorch - PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)
blended-latent-diffusion - Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]
diffusion_models - Minimal standalone example of diffusion model
seed-alchemy - Frontend UI and Backend Server for Stable Diffusion models
audio-diffusion - Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead of images.
Frido - Research code for paper "Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis"