Layout preserving realistic interior design using text and image prompts
A custom interior design pipeline API that combines Realistic Vision V3.0 inpainting pipeline with segmentation and MLSD ControlNets. This repo uses Cog to create a dockerized API. See the Replicate demo to test the running API.
You will need to have Cog and Docker installed to serve your model as an API. To run a prediction:
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:
cog run -p 5000 python -m cog.server.http
The API input arguments are as follows:
This is a custom pipeline inspired by AICrowd's Generative Interior Design hackathon that uses Realistic Vision V3.0 as the base model. See the base and ControlNet model pages for their respective licenses. This code base is licensed under the MIT license.
From neuralwork with :heart: