fast-stable-diffusion
EveryDream-trainer
fast-stable-diffusion | EveryDream-trainer | |
---|---|---|
239 | 32 | |
7,316 | 501 | |
- | - | |
8.6 | 2.4 | |
20 days ago | about 1 year ago | |
Python | Jupyter Notebook | |
MIT License | 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.
fast-stable-diffusion
-
Working Colab notebooks for training Dreambooth?
I tried using TheLastBen's fast dreambooth trainer. I managed to train a ckpt file but I can't run it.
-
Running AUTOMATIC1111 on Google Colab
You have a colab from ThelastBen It uses to be thes best at the time when auto1111 was working in google colab free. https://github.com/TheLastBen/fast-stable-diffusion
- Stability AI releases its latest image-generating model, Stable Diffusion XL 1.0
-
Google Colab disconnects after 5 mins of hosting A1111
Using https://github.com/TheLastBen/fast-stable-diffusion
-
I'm kinda new to all of this and just wanted to ask... How can I fix something like this? Tried inpaint but didn't work even after changing parameters and img2img make it lose quality...
This repo offers a template how to start with SD on runpod https://github.com/TheLastBen/fast-stable-diffusion. But I know how to code, si I made my own solution.
-
Unable to use ControlNet on AUTO1111 GUI - Google Colab Notebook
I can confirm I'm using the latest version of the colab notebook of this repo (https://github.com/TheLastBen/fast-stable-diffusion). Anyone can point to any solutions to this problem? Thanks in advance!
- Automatic 1111 not working
-
Useful Links
TheLastBen's Fast DB SD Colabs, +25-50% speed increase, AUTOMATIC1111 + DreamBooth
-
Can you use other base model to train your own model with TheLastBen or ShivamShrirao collab?
CalledProcessError Traceback (most recent call last) in () 182 wget.download('https://github.com/TheLastBen/fast-stable-diffusion/raw/main/Dreambooth/det.py') 183 print('Detecting model version...') --> 184 Custom_Model_Version=check_output('python det.py '+sftnsr+' --MODEL_PATH '+MODEL_PATH, shell=True).decode('utf-8').replace('\n', '') 185 clear_output() 186 print(''+Custom_Model_Version+' Detected')
-
How to Install and Run Stable Diffusion in Automatic1111 with Deforum in Google Collab?
have you tried https://github.com/TheLastBen/fast-stable-diffusion ?
EveryDream-trainer
- How should I train Dreambooth to understand a new class?
- SDTools v1.5
-
Guide on finetuning a model with mid-sized dataset of family pictures
https://github.com/victorchall/EveryDream-trainer Haven't tried it myself.
-
I've been collecting millions of images of only public domain /cc0 licensing. I'd like to train a stable diffusion model on the collection. Could some one share their knowledge of what this would take? Otherwise, simply enjoy my library.
In terms of training, you've got some really good links and comments to youtube tutorials, but if you're interested in more information about finetuning a model (as opposed to training from scratch), this is a good repo that has a lot of tools for finetuning, including an auto-captioner using BLIP and automatic file renaming. This is the actual finetuning repo.
-
Alternative tools to fine tune stable diffusion models?
Every Dream Trainer: Is basically a Dreambooth combine with Fine Tunning, so you can train multiples thing and a lot images: https://github.com/victorchall/EveryDream-trainer
-
Training with Dreambooth Models and/or Training with Automatic 1111 Textural Inversion
If you have the GPU for it, I'd recommend training all three things at once with (for example) https://github.com/victorchall/EveryDream-trainer. It recommends using "ground truth" training images - i.e. images from LAION-5B, which Stable Diffusion was originally trained with to have better prior preservation (retaining the flexibility of the original model) while incorporating new concepts, potentially even several different concepts in a single training run.
-
Flexible-Diffusion. My first experiment with finetuning. A broad model with better general aesthetics and coherence for different styles! Scroll for 1.5 vs FlexibleDiffusion grids. (BTW, PublicPrompts.art is back!!!)
I used about 300 captioned images (mainly beautiful MJ stuff), and used https://github.com/victorchall/EveryDream-trainer on RunPod for finetuning
- What do you think is the right dataset size to train/refine on dreambooth?
-
Practice your christmas cookies before you bake with this SD 1.5 model
SD 1.5 512x512 model for making christmas style cookies of whatever you'd like. trained on 30 512x512 images with manual captions in everydream
-
Guide for train/finetune with different image sizes, not dreambooth
This is the good one: https://github.com/victorchall/EveryDream-trainer
What are some alternatives?
DeepFaceLab - DeepFaceLab is the leading software for creating deepfakes.
kohya_ss
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.
StableTuner - Finetuning SD in style.
stable-diffusion-tensorflow - Stable Diffusion in TensorFlow / Keras
EveryDream - Advanced fine tuning tools for vision models
efficient-dreambooth - [Moved to: https://github.com/smy20011/dreambooth-docker]
kohya-trainer - Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning
stable-diffusion-webui-docker - Easy Docker setup for Stable Diffusion with user-friendly UI
EveryDream2trainer
stable-diffusion - A latent text-to-image diffusion model
stable-diffusion-webui - Stable Diffusion web UI