OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Image & Video AI

Sd Interior Design

Sd Interior Design is a Python pipeline that generates or edits interior-design images from a reference room image and text prompt. It combines Realistic Vision V3.0 inpainting with room segmentation and MLSD ControlNets, and uses Cog to package the model as a Dockerized prediction API.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Sd Interior Design — OpenViST project profile in Image & Video AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want to generate an interior-design concept from a room image and prompt, or need a documented Cog-based API pipeline to adapt for that task.

Who it is for

  • Interior designers exploring visual concepts from existing room photos.
  • Developers building image-generation workflows that need a room-image and prompt API.
  • Teams evaluating a self-served Cog and Docker pipeline for interior-design image generation.

Documented uses

  • Re-render a room photo according to a detailed design prompt.
  • Explore interior-design variations while using the source image as the generation reference.
  • Adjust prompt influence, generation guidance, inference steps, and seed through documented API inputs.
Before you choose

Requirements & limits

The repository is public and the code base is identified as MIT licensed. Serving the model requires Cog and Docker. A Replicate demo is linked in the README.

  • The reference image is a required API input alongside the text prompt.
  • The pipeline uses segmentation and MLSD ControlNets in addition to the Realistic Vision V3.0 inpainting pipeline.
  • The API exposes negative_prompt, num_inference_steps, guidance_scale, prompt_strength, and seed controls.
  • The README identifies the code as MIT licensed and directs readers to separate license terms for the base and ControlNet models.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run a prediction with Cog

Generate an interior-design image from a reference room image and a text prompt.

Before you start

  • Cog and Docker installed
  • A reference image; the repository example uses test_images/bedroom_3.jpg
  • A descriptive prompt

Steps

  1. Open the repository in an environment with Cog and Docker installed.

  2. Run the documented cog predict command with an image input and a prompt describing the desired room.

  3. Optionally provide documented inputs such as a negative prompt, inference steps, guidance scale, prompt strength, or seed.

Expected outcome

Cog runs a prediction using the supplied room image and prompt.

Guide limitations

  • The README does not specify the prediction output format or provide performance guarantees.
  • The base and ControlNet models have separate license terms from the MIT-licensed code.
Documentation 1 ↗
Source-based practical guide

Start the local Cog HTTP server

Serve the model as an API using the repository's documented Cog server command.

Before you start

  • Cog and Docker installed

Steps

  1. Open the repository in an environment with Cog and Docker installed.

  2. Run cog run -p 5000 python -m cog.server.http.

Expected outcome

The documented Cog HTTP server starts on port 5000 to serve the model as an API.

Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
alaradirik/sd-interior-design · Official homepage title · retained in its source language
How we review sourcesSuggest a correction