daam
LECO
daam | LECO | |
---|---|---|
4 | 1 | |
607 | 289 | |
3.6% | - | |
5.5 | 7.8 | |
about 1 month ago | 4 months ago | |
Jupyter Notebook | Jupyter Notebook | |
MIT License | 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.
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
LECO
-
Unified Concept Editing in Diffusion Models
Editing models in seconds. This is an upgrade to the lora sliders (https://erasing.baulab.info and https://github.com/p1atdev/LECO) but faster training with no damage to the model prior knowledge! Check out their code: https://github.com/rohitgandikota/unified-concept-editing
What are some alternatives?
Rerender_A_Video - [SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation
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.
infinite-zoom-stable-diffusion - resources for creating Ininite zoom video using Stable Diffiusion, you can use multiple prompts and it is easy to use.
erasing - Erasing Concepts from Diffusion Models
stable-diffusion-docker - Run the official Stable Diffusion releases in a Docker container with txt2img, img2img, depth2img, pix2pix, upscale4x, and inpaint.
lora - Using Low-rank adaptation to quickly fine-tune diffusion models.
unified-concept-editing - Unified Concept Editing in Diffusion Models
blended-latent-diffusion - Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]
LCM-LoRA - LCM LoRA