The library `pared` down the features of `diffusers` implemented the minimum function to generate images without using huggingface/diffusers to understand the inner workings of the library.
Project description
PareDiffusers
The library pared
down the features of diffusers
implemented the minimum function to generate images without using huggingface/diffusers to understand the inner workings of the library.
Why PareDiffusers?
PareDiffusers was born out of a curiosity and a desire to demystify the processes of generating images by diffusion models and the workings of the diffusers library.
I will write blog-style notebooks understanding how works using a top-down approach. First, generate images using diffusers to understand the overall flow, then gradually replace code with Pytorch code. In the end, we will write the code for the PareDiffusers code that does not include diffusers code.
I hope that it helps others who share a similar interest in the inner workings of image generation.
Versions
- v0.0.0: After Ch0.0.0, without StableDiffusionPipeline.
Table of Contents
Ch0.0.0 PareDiffusersPipeline
version: v0.0.0
- Generate images using diffusers
- Without StableDiffusionPipeline
- Without DDIMScheduler
- Without UNet2DConditionModel
- Without AutoencoderKL
Ch0.0.1 Test parediffusers
- Test PareDiffusersPipeline by pip install parediffusers.
Ch0.0.2 Play prompt_embeds
- Play prompt_embeds, make gradation images by using two prompts.
Ch0.1.0: PareDDIMScheduler
version: v0.1.3
- Generate images using diffusers
- Without StableDiffusionPipeline
- Without DDIMScheduler
- Without UNet2DConditionModel
- Without AutoencoderKL
Ch0.1.1: Test parediffusers
- Test PareDiffusersPipeline by pip install parediffusers.
Usage
import torch
from parediffusers import PareDiffusionPipeline
device = torch.device("cuda")
dtype = torch.float16
model_name = "stabilityai/stable-diffusion-2"
pipe = PareDiffusionPipeline.from_pretrained(model_name, device=device, dtype=dtype)
prompt = "painting depicting the sea, sunrise, ship, artstation, 4k, concept art"
image = pipe(prompt)
display(image)
Contribution
I am starting this project to help me understand the code in order to participate in diffusers' OSS. So, I think there may be some mistakes in my explanation, so if you find any, please feel free to correct them via an issue or pull request.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for parediffusers-0.2.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | cb71cf72eef0a7344ca2bb55206c8810aa4ebec430746fff6a4dfa813b556655 |
|
MD5 | 3a93fe8243b454c7758ab40195f09ac5 |
|
BLAKE2b-256 | ee05a696ee07efa7cb914c776240d2852e097ecc4049bbe308b190d2a3190163 |