StylePile
Dreambooth-Stable-Diffusion
StylePile | Dreambooth-Stable-Diffusion | |
---|---|---|
24 | 100 | |
569 | 3,170 | |
- | - | |
3.3 | 6.8 | |
about 1 year ago | 4 months ago | |
Python | Jupyter Notebook | |
GNU General Public License v3.0 only | 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.
StylePile
-
Prompt Syntax Language--I know I saw it, but where?
I found some of the images I remember from the article I'm trying to find, buried deep in the StylePile Extension , but sadly not the article itself. The Wildcards Directory Extension looks promising as well, although it seems only tangentially related to what I'm looking for.
-
What's "style pile"?
This then: GitHub - some9000/StylePile: A prompt generation helper script for AUTOMATIC1111/stable-diffusion-webui and compatible forks
-
I made an autoprompter as an extension for Automatic1111: One Button Prompt
The bulk of the inspiration and options came from the following sources: the Stylepile extension (personal favorite), this SD artists list , the amazing prompt book, and this ai art modifier guide
-
My guide on how to generate high resolution and ultrawide images
use the StylePile script (either use the link or install it using the extensions tab in the web-ui) and set the image type and direction to random
-
A simple prompt composer UI
I currently use StylePyle (https://github.com/some9000/StylePile) but I could see switching over to this if it had more artist/style options.
-
My SSD amazement space is running out and I don't find the cause.
If you have StylePile installed it has a bug where it creates gigabytes of useless files in %appdata%. See this issue on github: StylePile creating tons of images in \AppData\Local\Temp · Issue #37 · some9000/StylePile (github.com)
- Female portrait by Inkpunk(hypernetwork) + inkpunk768(embanding) + SD-2-MJart(embanding) in SD 2.1 768 model
-
Release: New Embedding for 2.0 and 2.1 - painted_abstract - an abstract style with high deatail, but still recognizable content
i used mostly StylePile to generate a lot of random promts
- How do you organize your tokens and other SD things?
- My script StylePile has received a bunch of updates and is now an extension for AUTOMATIC1111' s UI. Select image Type, Direction, Mood, Colors, Artists, Art movements from dropdowns. Insert variables, insert random elements, select strengths. Randomly pick almost any settings to get inspired.
Dreambooth-Stable-Diffusion
-
Will there be comprehensive tutorials for fine-tuning SD XL when it comes out?
Tons of stuff here, no? https://github.com/JoePenna/Dreambooth-Stable-Diffusion/
-
Useful Links
Joe Penna's Dreambooth (Tutorial|24GB) Most popular DB repo with great results.
-
Dreambooth / Custom Training / Model - what's the state of the art?
1) The https://github.com/JoePenna/Dreambooth-Stable-Diffusion instructions say to use the 1.5 checkpoints - is that the latest? Can I use the 2+ models or?
-
My Experience with Training Real-Person Models: A Summary
I quickly turned to the second library, https://github.com/JoePenna/Dreambooth-Stable-Diffusion, because its readme was very encouraging, and its results were the best. Unfortunately, to use it on Colab, you need to sign up for Colab Pro to use advanced GPUs (at least 24GB of VRAM), and training a model requires at least 14 compute units. As a poor Chinese person, I could only buy Colab Pro from a proxy. The results from JoePenna/Dreambooth-Stable-Diffusion were fantastic, and the preparation was straightforward, requiring only <=20 512*512 photos without writing captions. I used it to create many beautiful photos.
- I Used Stable Diffusion and Dreambooth to Create an Art Portrait of My Dog
- training
-
Training a model on Iwanaga Kotoko (from in/spectre), which step do you guys think the model is at its best?
I've found EveryDream to be brilliant and have switched from JoePenna's Dreambooth because I've found I get better results so long as I provide good captions for all the images, even if preparing the dataset takes 3x as long (took me 2 hours to crop and label the 54 images).
-
Dreambooth training results for face, object and style datasets with various prior regularization settings.
From what I know you can train with whatever size you want. But you need software that will support it. For example, ShivamShrirao/diffusers repo seems to allow a change of dimension. Also, you need HW that would support the training, because bigger images need more VRAM, for example,Joe Penna repo is using ~23GB with 512x512px so probably it's not a valid option. But the ShivamShrirao repo has optimizations that allow to run it with less VRAM.
-
Starting to get quite good results with Dreambooth. What do you think? (Follow @RokStrnisa on Twitter for more.)
This is a good starting place: https://github.com/JoePenna/Dreambooth-Stable-Diffusion
- I'm a N00b with training stuff. Trying to get runpod with Dreambooth training some images (80 total) and I'm getting this error. Help?
What are some alternatives?
civitai - A repository of models, textual inversions, and more
Dreambooth-SD-optimized - Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
A1111-Web-UI-Installer - Complete installer for Automatic1111's infamous Stable Diffusion WebUI
Stable-Diffusion-Regularization-Images - For use with fine-tuning, especially the current implementation of "Dreambooth".
a1111-sd-webui-tagcomplete - Booru style tag autocompletion for AUTOMATIC1111's Stable Diffusion web UI
StableDiffusion-Windows-GUI
OnnxDiffusersUI - UI for ONNX based diffusers
stable-diffusion-webui - Stable Diffusion web UI [Moved to: https://github.com/Sygil-Dev/sygil-webui]
fast-stable-diffusion - fast-stable-diffusion + DreamBooth
InvokeAI - InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.