diffusers
diffusers
diffusers | diffusers | |
---|---|---|
105 | 4 | |
1,870 | 50 | |
- | - | |
7.0 | 0.0 | |
11 months ago | about 1 year ago | |
Python | ||
Apache License 2.0 | 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.
diffusers
-
Useful Links
ShivamShrirao's Diffusers Pretrained diffusion models across multiple modalities.
-
DreamBooth fine-tuning failing to get the style
Like the title say I'm trying to fine-tune a model to match a style of a popular manhwa. I'm using the ShivamShrirao Google Colab to accomplish this.
-
How to resume Dreambooth training?
I am running the DreamBooth_Stable_Diffusion.ipynb notebook from ShivamShrirao locally on my machine. Let's say I have trained for 500 iterations and it hasn't converged yet. How do I make it resume training from that iteration so it can do another 500?
-
Non web-ui colab
My understanding, based on messages from an (alleged) representative of colabs, is that the webui is the problem, not SD itself. This also seems to be the consensus in the comments section of other posts. I have not yet seen a link to colab based webui alternatives so here is something I found from a tutorial. I am certain that there are better alternatives. Anyone have a better idea? This will still probably be useful to other people like me who are just messing around.
- [Stablediffusion] Guide pour DreamBooth avec 8 Go de vram sous Windows
-
Finally got Dreambooth running without errors... but is it even using the model I trained?
I'm running ShivamShrirao's fork of diffusers; ran into a fp16 issue and had to patch in a fix from the main branch ( #1567 ).
-
Shivam Stable Diffusion: Getting same example models repeatedly (SD + Dreambooth)
I am running Shivam Stable Diffusion Jupyter notebook: diffusers/DreamBooth_Stable_Diffusion.ipynb at main · ShivamShrirao/diffusers · GitHub.
- Running Stable Diffusion locally with personalized changes
- Can't create embedding's with dreambooth ckpt
-
Weird issue using Shivam's Diffuser notebook
Are you using this one? https://github.com/S
diffusers
- [Stablediffusion] Formation DreamBooth en moins de 8 Go de VRAM et inversion textuelle sous 6 Go
-
What does it mean to "train models"? Is this something I can do locally?
Training locally with 8GB of vram isn't easy to achieve without major optimizations, this repo uses DeepSpeed to get there but I couldn't make it work on my 1070 on Windows under WSL. Shivam's Colab notebook is a great alternative to local though.
-
I decided to retrain default Sadie Sink and this is the before and after result from the same seed.
There was a repo share here recently that uses Microsoft's DeepSpeed to improve memory optimizations and it got really close to be functional but I still get out of memory errors with it.
-
DreamBooth training in under 8 GB VRAM and textual inversion under 6 GB
Dreambooth training repository: https://github.com/Ttl/diffusers/tree/dreambooth_deepspeed
What are some alternatives?
stable-diffusion-webui - Stable Diffusion web UI
fast-stable-diffusion - fast-stable-diffusion + DreamBooth
A1111-Web-UI-Installer - Complete installer for Automatic1111's infamous Stable Diffusion WebUI
xformers - Hackable and optimized Transformers building blocks, supporting a composable construction.
efficient-dreambooth - [Moved to: https://github.com/smy20011/dreambooth-docker]
Dreambooth-Stable-Diffusion - Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) by way of Textual Inversion (https://arxiv.org/abs/2208.01618) for Stable Diffusion (https://arxiv.org/abs/2112.10752). Tweaks focused on training faces, objects, and styles.
Dreambooth-SD-optimized - Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
Dreambooth-Stable-Diffusion - Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
dreambooth-gui
diffusionbee-stable-diffusion-ui - Diffusion Bee is the easiest way to run Stable Diffusion locally on your M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed.
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
diffusers - 🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.