Add an example Google Colab / Jupyter Notebook file

[0xdevalias]

Similar to:

• Please make a Dockerfile #4

[0xdevalias]

Related:

• COLLAB LINK for base model inference #16

colab.research.google.com/drive/1cuzz-TcAXsqlCPqqa8U7LltMmeZuBYkh?usp=sharing

[0xdevalias]

Should work now, make sure you check the box "redownload original model" when choosing V2

https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb

Requires more than 12GB of RAM for now, so free colab probably won't suffice.

Originally posted by @TheLastBen in TheLastBen/fast-stable-diffusion#599 (comment)

[inflamously]

@0xdevalias Hello there, I hope is it fine for you that I kind of created a "minified" version of your colab which works fine with a T4 using xformers.
Sometimes later I might add other tools like Inpainting, Depth and Upscaling.

https://colab.research.google.com/drive/1wzI9nt8dYqq47I1Y-WvOAiO01y7EBoiO?usp=sharing

[backnotprop]

Here is a Colab/Gradio setup to play with the depth model:

https://github.com/backnotprop/Colab-Stable-Diffusion-2-Depth-UI/tree/main

[0xdevalias]

I hope is it fine for you that I kind of created a "minified" version of your colab which works fine with a T4 using xformers.

@inflamously It's not my colab, just one I found on another repo and wanted to ensure was linked and accessible here :)

[0xdevalias]

The inpainting model should work now without needing to rename the checkpoint.
For anyone who wants to try it: https://colab.research.google.com/drive/1ayH6PUri-vvTXhaoL3NEZr_iVvv2qosR

Originally posted by @uservar in AUTOMATIC1111/stable-diffusion-webui#5011 (comment)

[0xdevalias]

Yes, stable_diffusion2 is working now. And the few lines of code to get inference is in here:
https://colab.research.google.com/drive/1Na9x7w7RSbk2UFbcnrnuurg7kFGeqBsa?usp=sharing

Originally posted by @hamzafar in huggingface/diffusers#1388 (comment)

!pip install --upgrade git+https://github.com/huggingface/diffusers.git transformers accelerate scipy

from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler
import torch

model_id = "stabilityai/stable-diffusion-2"

# Use the Euler scheduler here instead
scheduler = EulerDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
pipe = StableDiffusionPipeline.from_pretrained(model_id, scheduler=scheduler, revision="fp16", torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "beautiful gaze"

image = pipe(prompt, height=768, width=768).images[0]

image

[woctezuma]

Alternatively, run stable_diffusion.ipynb.