EveryDream2trainer
stable-diffusion-webui-wd14-tagger
EveryDream2trainer | stable-diffusion-webui-wd14-tagger | |
---|---|---|
48 | 15 | |
753 | 888 | |
- | - | |
9.2 | 8.6 | |
8 days ago | 10 months ago | |
Python | Python | |
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.
EveryDream2trainer
- Question on SD Finetuning
-
80% Completed!
I'm using EveryDream2 with SD v1 based models. You can define whatever resolution you want for training, as long as your Vram allows it.
-
Freedom. Finetuned 2.1 that can gen (+1024x) and often without negative. Release this or next week. Demo available for testing in next days. Here are some creations from a closed beta that I released on Twitter yesterday. 20 people, 3 hours, 1500 gens. I hope you enjoy. More on imgur album.
There is a demo optimizers settings here that uses special settings for the text encoder: https://github.com/victorchall/EveryDream2trainer/blob/main/optimizerSD21.json
- Can we clear up the regularization images concept once and for all?
-
Are there any recent, or still relevant, tutorials on training LoRAs within Dreambooth? Any specific / special settings to take advantage of my 4090?
If you have a large dataset of pictures, I'd recommend https://github.com/victorchall/EveryDream2trainer instead of Dreambooth. It has decent documentation (well for an open source project that is) and it has a very nice validation feature (disabled by default) which actually gives you good feedback on how the training is progressing.
-
Train a model from 300k images?
EveryDream2 can handle this. They even have tools to help you autocaption using BLIP. https://github.com/victorchall/EveryDream2trainer
- [Dreambooth] The docs for this Dreambooth-like trainer, Everydream2
- Resources for artists interesting in using StableDiffusion as a tool?
- Is Joe Penna's DreamBooth still the best option for training photorealistic persons or faces?
-
Can we identify most Stable Diffusion Model issues with just a few circles?
I recoment EveryDream2 for training, it has a lot of nice features. I'm not sure there is a proper manual to learn how to train, but there is a lot of information available. I have been learning this subjects for a few months myself.
stable-diffusion-webui-wd14-tagger
- CLIP and DeepDanbooru Alternatives For Prompt Generation [Relevant Self-Promotion]
-
Ideas for extensions?
Create an extension like 'send pictures' that uses the WD14 tagger which is way more detailed and has options for nsfw etc. Its used in Automatic1111 and Koyha ss so there's extensions you can probably implement from. https://github.com/toriato/stable-diffusion-webui-wd14-tagger
-
vladmandic-WD14-Tagger
If anyone is interested I made some changes to toriato's wd14-tagger, now it works also on vladmandic webui, repo here. You can do a new installation, or use your old automatic1111 one changing 3 files, instructions on my repo. The lora files also work (there were some problems in the vlad issue page). I'm not a programmer and it's not perfect though, in fact for now if you don't like the default tagger model you have to change it manually (instructions in the repo), and since it is basically a fork of toriato's version, if there were errors there, there will be here too.
-
Community-trained SD 1.6 Model, can we do it?
Automatic captioning tools that can be used as an initial point for captions: this tool or this one.
- Is anyone able to make the tagger extension compatible with Vlad UI ?
-
What are your favorite Extensions?
wd14-tagger, to describe anime images and get a prompt idea
-
Experiment AI Anime w/ C-Net 1.1 + GroundingDINO + SAM + MFR (workflow)
Use WD 1.4 tagger (https://github.com/toriato/stable-diffusion-webui-wd14-tagger) to extract prompt words from each frame (threshold 0.65), then use the dataset tag editor (https://github.com/toshiaki1729/stable-diffusion-webui-dataset-tag-editor) for batch editing, mainly:
-
Currently getting better results with Kohya ss Loras (Lycoris Locon) than with DB, am I alone?
I recommend using EveryDream2. You'll need an 11GB VRAM GPU. There's no need to crop or resize images, just caption them, which can be done automatically with CLIP Interrogator or WD14 taggers. Make sure to add the trigger word for your subject. It's not a Dreambooth script; it's actual training, so it shouldn't be as destructive to the model as Dreambooth. Typically, using an LR of 1e-6 with a cosine scheduler over two epochs and a batch size of 4 works fine. This script supports validation, so you can actually watch in real-time whether the training is going well or if you're overfitting. I got very good results using it.
-
For Lora training, isn’t there a good AI that discribes the pictures you want to use for training?
In my current process, I use CLIP Interrogator to produce a high level caption and wd14 tagger for more granular booru tags. Typically in that order, because you can append the results from the latter to the former. Both tools perform with greater accuracy than the standard interrogators in img2img and give you more flexibility and features as well. You still have to do some manual adjustments, but I generally prefer this process over starting from scratch.
- Captioning LoRA's
What are some alternatives?
ComfyUI - The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.
clip-interrogator - Image to prompt with BLIP and CLIP
StableTuner - Finetuning SD in style.
batch-face-swap - Automaticaly detects faces and replaces them
sd-scripts
sd_dreambooth_extension
EveryDream-trainer - General fine tuning for Stable Diffusion
stable-diffusion-webui - Stable Diffusion web UI
kohya-trainer - Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning
automatic - SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models
fast-stable-diffusion - fast-stable-diffusion + DreamBooth
stable-diffusion-webui-dataset-tag-editor - Extension to edit dataset captions for SD web UI by AUTOMATIC1111