Giter VIP home page Giter VIP logo

stable_diffusion_dreambooth_inpainting's Introduction

Stable Diffusion Dreambooth Inpainting Finetuning ๐ŸŽจ๐Ÿช„

inpainting_dog

This repository provides an engaging illustration on how to unleash the power of Stable Diffusion to finetune an inpainting model with your own images.

Inpainting, simply put, it's a technique that allows to fill in missing parts of an image. By leveraging fine-tuning you to replace any custom mask on your image with the finetuned object, offering you the reigns to create custom scenarios that depict your finetuned object.

Try it out:

Open In Colab

Why should you finetune an inpainting model? ๐Ÿš€

This technique can be particularly useful for marketers, sellers, and content creators who'd love to experiment with images. For instance, in the context of e-commerce, it is possible to generate striking images of your products in curated scenarios or by showcasing your products as worn by digital human models.

Stable Diffusion inpainting example for e-commerce below:

Open In Colab

ecommerce_necklace ecommerce_necklace

Stable Diffusion XL inpainting example for e-commerce below:

Open In Colab

stable_diffusion_dreambooth_inpainting's People

Contributors

davide97l avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

stable_diffusion_dreambooth_inpainting's Issues

No file model_index.json is found

I am trying to run the Colab notebook stable_diffusion_dreambooth_inpaint.ipynb. While trying to generate images from finetuned model
pipe = StableDiffusionInpaintPipeline.from_pretrained(
"stable-diffusion-inpainting-dog",
torch_dtype=torch.float16,
)

I am getting the error:

OSError Traceback (most recent call last)
in <cell line: 6>()
4
5
----> 6 pipe = StableDiffusionInpaintPipeline.from_pretrained(
7 "model",
8 torch_dtype=torch.float16,

3 frames
/usr/local/lib/python3.10/dist-packages/diffusers/configuration_utils.py in load_config(cls, pretrained_model_name_or_path, return_unused_kwargs, return_commit_hash, **kwargs)
368 config_file = os.path.join(pretrained_model_name_or_path, subfolder, cls.config_name)
369 else:
--> 370 raise EnvironmentError(
371 f"Error no file named {cls.config_name} found in directory {pretrained_model_name_or_path}."
372 )

OSError: Error no file named model_index.json found in directory model.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.