memory_efficient_dreambooth
Dreambooth-Stable-Diffusion-cpu
memory_efficient_dreambooth | Dreambooth-Stable-Diffusion-cpu | |
---|---|---|
2 | 6 | |
55 | 14 | |
- | - | |
10.0 | 10.0 | |
over 1 year ago | over 1 year ago | |
Python | Jupyter Notebook | |
- | 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.
memory_efficient_dreambooth
-
Dreambooth: Are more images better?
Yeah, all were the same subject. I used this script for running dreambooth https://github.com/matteoserva/memory_efficient_dreambooth and to my understanding this does not use the class images at all. I had another training earlier with 1400 faces only @ 20k steps which had much better results. Maybe I should've used 40k steps? I don't know :)
-
Dreambooth in 11GB of VRAM
This is my repository with the updated source and a sample launcher: https://github.com/matteoserva/memory_efficient_dreambooth
Dreambooth-Stable-Diffusion-cpu
-
Should I use the CPU only dreambooth?
I got a GTX 1650 with 4GB VRAM, which isn't really that good for training. My i5-4670 isn't the most efficient either, but it would still be possible to use. Is the CPU only option in the regular dreambooth out do I have to get this version: https://github.com/andreae293/Dreambooth-Stable-Diffusion-cpu
-
Dreambooth on <12GB locally?
I haven't seen any optimizations on the JoePenna or gammagec forks. They are still at 24GB. NMKD mentioned possibly optimizing it more, now that it's included in that GUI. There's also a CPU-only version. I don't really understand the differences between these (which all come from XavierXiao) and the diffusers versions - is it just more optimization or are they fundamentally different?
-
Is it possible to fine tune with a 6GB GPU?
There is a CPU-only fork: https://github.com/andreae293/Dreambooth-Stable-Diffusion-cpu. Needs a lot (35-40GB) of RAM. It works like the JoePenna version, not the diffusers version. I don't fully understand the differences between the two, besides that the diffusers version has been more heavily optimized for low VRAM.
-
Has anyone had luck on 10 gb vram following this local dreambooth video guide?
if you're willing to wait for it to process you could do what i'm doing (i have a 2070 with 8gb vram) and try this one - https://github.com/andreae293/Dreambooth-Stable-Diffusion-cpu
-
Dreambooth in 11GB of VRAM
This https://github.com/andreae293/Dreambooth-Stable-Diffusion-cpu I believe should produce as ckpt file. You're probably testing the CPU on the hugging face version.
-
Dreambooth Stable Diffusion training in just 12.5 GB VRAM, using the 8bit adam optimizer from bitsandbytes along with xformers while being 2 times faster.
Just found this one: https://github.com/andreae293/Dreambooth-Stable-Diffusion-cpu
What are some alternatives?
stable-dreambooth-optimized - Dreambooth implementation based on Stable Diffusion with minimal code.
efficient-dreambooth - [Moved to: https://github.com/smy20011/dreambooth-docker]
diffusers - 🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
bitsandbytes - Accessible large language models via k-bit quantization for PyTorch.
fast-stable-diffusion - fast-stable-diffusion + DreamBooth
xformers - Hackable and optimized Transformers building blocks, supporting a composable construction.
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.
diffusers - 🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
xformers_wheels