|
--- |
|
license: creativeml-openrail-m |
|
library_name: diffusers |
|
pipeline_tag: text-to-image |
|
--- |
|
# SD 1.5 Big G (alpha) |
|
|
|
This is a Stable Diffusion 1.5 model, but it uses the [CLIP Big G](https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k) text encoder instead of the original [CLIP-L](https://huggingface.co/openai/clip-vit-large-patch14) text encoder. |
|
This is just a knowledge transfer pre-train with the goal of preserving the current knowledge of the model. |
|
It was only trained using student/teacher training from my [SD 1.5 fine tune, Objective Reality v2](https://huggingface.co/ostris/objective-reality). |
|
To fully realize the full potential of the much larger text encoder, it would need to be further fine tuned on a large dataset. |
|
|
|
# Examples |
|
|
|
Coming soon |
|
|
|
# Usage |
|
|
|
For diffusers, you can use it like any other stable diffusion model. |
|
|
|
```python |
|
from diffusers import StableDiffusionPipeline |
|
import torch |
|
|
|
model_id = "ostris/sd15-big-g-alpha" |
|
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16) |
|
pipe = pipe.to("cuda") |
|
|
|
prompt = "a photo of an astronaut riding a horse on mars" |
|
image = pipe(prompt).images[0] |
|
|
|
image.save("astronaut_rides_horse.png") |
|
``` |
|
|
|
It will not work out of the box with Comfy UI or Auto1111. There would need to be special code to load it. If there is any interest in this model, I may work on compatibility. |
|
Overall, it won't be hard to add. The only architecture change is the text encoder the and cross attention weights. |
|
|
|
# Alpha |
|
|
|
This is just a pretrained alpha. There are some concepts that did not seem to transfer. It really needs proper training on a large dataset. Anyone is welcome to take this task on. I do not plan to at the time. |
|
|
|
# Why make this? |
|
|
|
In the words of George Mallory, "Because it's there" |
|
|
|
# Training Method |
|
|
|
As mentioned above, it was trained using student/teacher only. This was an iterative process over the corse of a few months, and I did not keep track of all of the exact numbers. The following are best estimates. |
|
|
|
The cross attention layers were trained for 1-2 million steps with a batch size of 8 on a single 4090 GPU. Then the full unet was trained for around 100k steps with the same settings. |
|
|
|
|
|
|
