blended-latent-diffusion
daam
| blended-latent-diffusion | daam | |
|---|---|---|
| 1 | 4 | |
| 514 | 607 | |
| - | 3.6% | |
| 4.5 | 5.5 | |
| 5 months ago | about 1 month 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.
blended-latent-diffusion
-
Blended Latent Diffusion's code has been released.
The research paper https://arxiv.org/abs/2206.02779 has finally released their code https://github.com/omriav/blended-latent-diffusion after I asked about it 2 days ago in an issue.
daam
- q: can I somehow validate my prompt as meaningful?
-
Patchouli is kind of a vibe, tbh
I did see this recently, where it can generate a heatmap of what an addition to a prompt changed in the image, but I haven't tried it yet, and that's not exactly much of an an explanation anyways
-
[R] What the DAAM: Interpreting Stable Diffusion and Uncovering Generation Entanglement
Paper: What the DAAM: Interpreting Stable Diffusion Using Cross Attention (arXiv paper, codebase)
-
[Discussion] Approach for applying Explainable AI on Diffusion Models
Found relevant code at https://github.com/castorini/daam + all code implementations here
What are some alternatives?
Kandinsky-2 - Kandinsky 2 — multilingual text2image latent diffusion model
Rerender_A_Video - [SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation
Diffusion-Models-Papers-Survey-Taxonomy - Diffusion model papers, survey, and taxonomy
infinite-zoom-stable-diffusion - resources for creating Ininite zoom video using Stable Diffiusion, you can use multiple prompts and it is easy to use.
LECO - Low-rank adaptation for Erasing COncepts from diffusion models.
glami-1m - The largest multilingual image-text classification dataset. It contains fashion products.
stable-diffusion-docker - Run the official Stable Diffusion releases in a Docker container with txt2img, img2img, depth2img, pix2pix, upscale4x, and inpaint.
DiffusionFastForward - DiffusionFastForward: a free course and experimental framework for diffusion-based generative models
paint-with-words-sd - Implementation of Paint-with-words with Stable Diffusion : method from eDiff-I that let you generate image from text-labeled segmentation map.
MultiDiffusion - Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)
lora - Using Low-rank adaptation to quickly fine-tune diffusion models.