waifu-diffusion
improved-aesthetic-predictor
waifu-diffusion | improved-aesthetic-predictor | |
---|---|---|
28 | 8 | |
1,926 | 707 | |
- | - | |
0.0 | 3.6 | |
about 1 year ago | 7 months ago | |
Python | Python | |
GNU Affero General Public License v3.0 | 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.
waifu-diffusion
- What exactly constitutes a new, different model?
- AI: "All Your Horny Belong to Us"
-
Cool Japan Diffusion 2.1.1 has been released! 🎉
It's slander to say that the WD team is milking donations in the same way UD is. They already have a public working model which they are continuing to train. The WD team has also implemented features like aspect ratio bucketing into their custom trainer. If they were really milking the project for donations they would have just used the base compvis trainer it was forked from.
-
From one of the original DreamBooth authors : Stop using SKS as the initializer word
Use one of the original SD repos, or the code for Waifu Diffusion, or the Smirkingface refactor.
- Stable Diffusion links from around October 4, 2022 that I collected for further processing
-
These images of Senko were Generated by AI (Part 2 - Halloween themed)
My model is based off waifu-diffusion.
-
What is the name of the AI that created anime art that people keep talking about?
waifu diffusion (free) and NovelAI (paid afaik) is what I know
-
Any finetuners (actual finetuning, not Dreambooth) here who can help me find a good learning rate and epoch? At batch size 12/16 (I am using a single A100) with a learning rate of 1e-5/1e-4 I am overfitting (turning all characters into my character) while the style still isn't there yet with ep14...
This is the one I use: https://github.com/harubaru/waifu-diffusion
-
Is there a way to tell the AI which artstyle to use?
This is called textual inversion which use many images and a small group of promtps to describe a single element, and there are two methods: with frozen model and with unfrozen model. The first one just creates a new “word” to “guide” the model, in other words, a word that means the same as a chunk of a prompt. The resulting data is a tiny file. The second one (better known dreamboth training) adds new data to de model, so it can copy the character’s characteristics and artist style more effecively resulting in a new model file (cpkt) There are not a single tutorial, so you can find many info on r/StableDiffusion. Also, there is a third method which is based on the original training (many images and its own description) Instruction are here: Training guide I don’t know if this guide is finished though
-
Tsukasa at the Beach (Created by a Waifu-Diffusion AI)
The model is a tweaked version of waifu-diffusion using textual inversion. Still not perfect but the AI can create pretty plausible images.
improved-aesthetic-predictor
- [D] Is accurately estimating image quality even possible?
-
[D] Looking for publicly available generative image datasets labeled with human preferences or scores. Any recommendations?
Perhaps you could use an "aesthetic-evaluator": https://github.com/christophschuhmann/improved-aesthetic-predictor (probably not SoTA but it works)
-
What are the current must-have extensions for Automatic1111?
"Calculates aesthetic score for generated images using CLIP+MLP Aesthetic Score Predictor based on Chad Scorer "
- Is there an AI which can judge the “aesthetic potential” of an image? [D]
-
Dreamer's Guide to Getting Started w/ Stable Diffusion!
stable-diffusion-v1-2: Resumed from stable-diffusion-v1-1. 515,000 steps at resolution 512x512 on "laion-improved-aesthetics" (a subset of laion2B-en, filtered to images with an original size >= 512x512, estimated aesthetics score > 5.0, and an estimated watermark probability < 0.5. The watermark estimate is from the LAION-5B metadata, the aesthetics score is estimated using an improved aesthetics estimator).
-
[P] Waifu-Diffusion: a Stable Diffusion model finetuned on 56k Danbooru images
The data used for fine-tuning has come from a random sample of 56k Danbooru images, which were filtered based on CLIP Aesthetic Scoring where only images with an aesthetic score greater than 6.0 were used.
-
Waifu-Diffusion v1-2: A SD 1.4 model finetuned on 56k Danbooru images for 5 epochs
All they've said is they randomly picked 56,000 images that had an aesthetic score greater than 6.0. The score is created by this model. https://github.com/christophschuhmann/improved-aesthetic-predictor
-
How to combine stable diffusion with a model which predicts aesthetics score?
Does anyone know how you could combine a model like Aesthetic Score Predictor with stable diffusion? They used this model to filter training images by score. Iit seems like a lot of people just tune their prompt to make images more aesthetic, by adding certain words.
What are some alternatives?
stable-diffusion - This version of CompVis/stable-diffusion features an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface, a WebGUI, and multiple features and other enhancements. [Moved to: https://github.com/invoke-ai/InvokeAI]
DiffusionToolkit - Metadata-indexer and Viewer for AI-generated images
stable-diffusion-webui - Stable Diffusion web UI
stable-diffusion - This version of CompVis/stable-diffusion features an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface, a WebGUI, and multiple features and other enhancements.
stable-diffusion-ui - Easiest 1-click way to install and use Stable Diffusion on your computer. Provides a browser UI for generating images from text prompts and images. Just enter your text prompt, and see the generated image. [Moved to: https://github.com/easydiffusion/easydiffusion]
discord-rpc-for-automatic1111-webui - Silent extension (no tab) for AUTOMATIC1111's Stable Diffusion WebUI adding connection to Discord RPC, so it would show a fancy table in the Discord profile.
stable-diffusion-webui - Stable Diffusion web UI [Moved to: https://github.com/sd-webui/stable-diffusion-webui]
sd-wildcards - A collection of wildcards for Stable Diffusion
merge-models - Merges two latent diffusion models at a user-defined ratio
stable-diffusion-webui-aesthetic-image-scorer
stable-diffusion-webui - Stable Diffusion web UI [Moved to: https://github.com/Sygil-Dev/sygil-webui]
stable-diffusion-webui-stable-horde - Stable Horde client for AUTOMATIC1111's Stable Diffusion Web UI