https://github.com/neuralwork/sd-interior-design
Layout preserving realistic interior design using text and image prompts
https://github.com/neuralwork/sd-interior-design
cog diffusion-models generative-ai image-editing interior-design realistic-vision stable-diffusion text-to-image
Last synced: 8 months ago
JSON representation
Layout preserving realistic interior design using text and image prompts
- Host: GitHub
- URL: https://github.com/neuralwork/sd-interior-design
- Owner: neuralwork
- License: mit
- Created: 2024-04-06T13:30:04.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-11-29T16:40:52.000Z (over 1 year ago)
- Last Synced: 2025-03-24T13:08:42.778Z (about 1 year ago)
- Topics: cog, diffusion-models, generative-ai, image-editing, interior-design, realistic-vision, stable-diffusion, text-to-image
- Language: Python
- Homepage:
- Size: 20.2 MB
- Stars: 88
- Watchers: 1
- Forks: 29
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
## RealisticVision for Interior Design
A custom interior design pipeline API that combines [Realistic Vision V3.0](https://huggingface.co/SG161222/Realistic_Vision_V3.0_VAE) inpainting pipeline with [segmentation](https://huggingface.co/BertChristiaens/controlnet-seg-room) and [MLSD](https://huggingface.co/lllyasviel/sd-controlnet-mlsd) ControlNets. This repo uses [Cog](https://github.com/replicate/cog/blob/main/docs/getting-started-own-model.md) to create a dockerized API. See the Replicate [demo](https://replicate.com/adirik/interior-design) to test the running API.
## Basic Usage
You will need to have [Cog](https://github.com/replicate/cog/blob/main/docs/getting-started-own-model.md) and Docker installed to serve your model as an API. To run a prediction:
```bash
cog predict -i image=@test_images/bedroom_3.jpg prompt="A bedroom with a bohemian spirit centered around a relaxed canopy bed complemented by a large macrame wall hanging. An eclectic dresser serves as a unique storage solution while an array of potted plants brings life and color to the room"
```
To start your server and serve the model as an API:
```bash
cog run -p 5000 python -m cog.server.http
```
The API input arguments are as follows:
- **image:** The provided image serves as a base or reference for the generation process.
- **prompt:** The input prompt is a text description that guides the image generation process. It should be a detailed and specific description of the desired output image.
- **negative_prompt:** This parameter allows specifying negative prompts. Negative prompts are terms or descriptions that should be avoided in the generated image, helping to steer the output away from unwanted elements.
- **num_inference_steps:** This parameter defines the number of denoising steps in the image generation process.
- **guidance_scale:** The guidance scale parameter adjusts the influence of the classifier-free guidance in the generation process. Higher values will make the model focus more on the prompt.
- **prompt_strength:** In inpainting mode, this parameter controls the influence of the input prompt on the final image. A value of 1.0 indicates complete transformation according to the prompt.
- **seed:** The seed parameter sets a random seed for image generation. A specific seed can be used to reproduce results, or left blank for random generation.
## Model Details
This is a custom pipeline inspired by AICrowd's Generative Interior Design [hackathon](https://www.aicrowd.com/challenges/generative-interior-design-challenge-2024) that uses [Realistic Vision V3.0](https://huggingface.co/SG161222/Realistic_Vision_V3.0_VAE) as the base model. See the base and ControlNet model pages for their respective licenses. This code base is licensed under the [MIT license](https://github.com/neuralwork/sd-interior-design/blob/main/LICENSE).
From [neuralwork](https://neuralwork.ai/) with :heart: