Wuerstchen
stable-diffusion-aesthetic-gradients
Wuerstchen | stable-diffusion-aesthetic-gradients | |
---|---|---|
1 | 14 | |
486 | 703 | |
- | - | |
5.9 | 10.0 | |
about 1 month ago | over 1 year ago | |
Jupyter Notebook | Jupyter Notebook | |
MIT License | GNU General Public License v3.0 or later |
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.
Wuerstchen
-
Like Diffusion but Faster: The Paella Model for Fast Image Generation
Fully correct, also the v2 of the paper introduced a model that is bigger and slower, however generates better images. So the 500ms was only for the first model we introduced in v1. I also want to mention our new work as it is very much related to this whole topic of "speeding up models" -> either training or sampling: Würstchen: https://github.com/dome272/wuerstchen/
stable-diffusion-aesthetic-gradients
-
Can anyone help me describe the style of this picture? I "accidentally" got this from the base 2.1 model with just a few words and can't recreate the style now.
You might want to try https://github.com/vicgalle/stable-diffusion-aesthetic-gradients to see if you can reproduce the style without necessarily having to come up with text descriptions
-
Is there a way that SD can combine 2 images together?
Aesthetic gradients plugin for Automatic1111 WebUI
-
Is it possible to Interrogate images not into text, but embeddings?
I think you're describing Aesthetic Gradients
- I'm a photographer with hundreds of thousands of photos of beautiful models, can I use these to improve my Stable Diffusion?
- Can SD users share trained embeddings? If so, is there a place to do so?
- A quick test of the Clip Aesthetic feature added to A11111
-
Aesthetic gradients feature has been added to AUTOMATIC1111 GitHub repo. Aesthetic gradients is a "computationally cheap" method of generating images in a style specified in a set of input images.
Its different imo. Look at the floral example flower_plant https://github.com/vicgalle/stable-diffusion-aesthetic-gradients
-
Aesthetic gradients: a "computationally cheap" method of generating images in a style specified in a set of input images without altering a model. Code for aesthetic gradients in Stable Diffusion has been released.
Also, since you have found some interesting aesthetic embeddings, if you wish, you can contribute your embeddings by opening a PR in the repo https://github.com/vicgalle/stable-diffusion-aesthetic-gradients !
-
I'm happy to announce that our first model, CSALPHA0, drops on Friday October 21st. But we need your support to host the ckpt file. Details inside.
We could definitely use some help with generating aesthetic gradient tensors if you think you'd like to take some of that on. It's a fairly straightforward process and it's all laid out in this repo. I would love to see what you come up with and how you implement it. The file output is a pytorch tensor so it's extremely small which makes it great for sharing with friends!
-
Is there a shortcut to this workflow?: generate an image, upscale it, regenerate just a cropped portion at the higher resolution, then stitch that regenerated portion onto the upscaled image?
You could look into generating your own aesthetic gradients using a dataset of people from a distance with faces you like in the style you're going for. Here's the repo. It's much more compute efficient than retraining over and over to adjust for overtraining with many tokens at a time. Although it can take some time adjusting your aesthetic steps. You should be able to get results! Just explore and have fun!
What are some alternatives?
Gen-L-Video - The official implementation for "Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising".
kohya-trainer - Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning
Paella - Official Implementation of Paella https://arxiv.org/abs/2211.07292v2
novelai-aspect-ratio-bucketing - Implementation of aspect ratio bucketing for training generative image models as described in: https://blog.novelai.net/novelai-improvements-on-stable-diffusion-e10d38db82ac
DreamArtist-sd-webui-extension - DreamArtist for Stable-Diffusion-webui extension
stable-diffusion - Heavily refactored version of the stable diffusion development repository. Used for the SmirkingFace project.
stable-diffusion-webui - Stable Diffusion web UI
japanese-stable-diffusion - Japanese Stable Diffusion is a Japanese specific latent text-to-image diffusion model capable of generating photo-realistic images given any text input.
stable-diffusion-webui-aesthetic-gradients - Aesthetic gradients extension for web ui