stable-diffusion-aesthetic-gradients
Personalization for Stable Diffusion via Aesthetic Gradients 🎨 (by vicgalle)
kohya-trainer
Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning (by Linaqruf)
stable-diffusion-aesthetic-gradients | kohya-trainer | |
---|---|---|
14 | 36 | |
703 | 1,772 | |
- | - | |
10.0 | 8.3 | |
over 1 year ago | about 2 months ago | |
Jupyter Notebook | Jupyter Notebook | |
GNU General Public License v3.0 or later | Apache License 2.0 |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
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.
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.
stable-diffusion-aesthetic-gradients
Posts with mentions or reviews of stable-diffusion-aesthetic-gradients.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-01-16.
-
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!
kohya-trainer
Posts with mentions or reviews of kohya-trainer.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-08-04.
-
Best method for training lora with sdxl
This longer colab notebook: I did use this one (or one of the slight derivatives of it) and got out a safetensors file, but the lora didn't work at all--I'd use it a increase it's weight but I just would see no effect
- Question on SD Finetuning
-
Requesting Help: Stable Diffusion with Dreambooth via Automatic1111
It isn't what you are asking for (sry) but I struggled with this thing for way too long until I found out about the Kohya Trainer. https://github.com/Linaqruf/kohya-trainer So much easier with a lot of videos by the various YT folks. Standalone WebUI that just works. Life is good here!
-
Do you need a PhD in AI for AI opportunities?
It's seem that he is stable diffusion model creators. In that space, it's less knowing about the code and more experimenting on what would happen in the training. The stable diffusion community has repertoire of fine-tuning tools that is accessible for someone who have no single idea on the code behind it, no different than using application like kohya.
-
Am I some kind of idiot? I cant for the life of me get Lora training to work on colab or runpod.
Have you tried out one of the colabs from https://github.com/Linaqruf/kohya-trainer ? The colabs themselves are pretty long, but you just have to read each step and then usually push the button to run that cell, then move on to the next one.
-
[Stable Diffusion] Diffusion stable sur Google Colab se bloque toujours!
** https: //github.com/linaqruf/kohya-trainer**
-
Lora training steps with large batch sizes?
There are a lot of variables that affect what kind of settings to use, but afaik the best solution to finding the right step count for what your training is still just to save multiple epochs and then run a x/y/z plot comparison. If you can't do that locally because of your 4gb card, you could try using Lora colabs that include inference capabilities.
-
Colab Troubles (Addendum)
You seem to be a little confused. You wont find an ipynb of a model. You would reference a model via a content portal like hugginface. If your model is hosted there, you dont have to download it to your computer or gdrive first. You just reference it with the hugginface-style reference, ie runwayml/stable-diffusion-v1-5. Some colabs will let you also reference a URL to pull down the model. Example. https://github.com/Linaqruf/kohya-trainer/blob/main/kohya-LoRA-dreambooth.ipynb. In that case, you can get the direct url to a checkpoint, for example at civit.ai. If you're decent at messing around with code, you can deconstruct that code block to use in a different colab. As for gdrive, it's only a couple dollars to get 100G.
- PNG info not copied from images generated through Kohya.
-
Is Colab going to start banning people who use it for Stable Diffusion????
Try this colab to train Lora, it can generate image without the UI too
What are some alternatives?
When comparing stable-diffusion-aesthetic-gradients and kohya-trainer you can also consider the following projects:
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
lora - Using Low-rank adaptation to quickly fine-tune diffusion models.