DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to edit a Blender scene with a local Ollama model with Blender AI Addon

Use Ollama instead of a cloud key to have the agent change objects in your scene.

  • Content
  • Advanced
  • 1 hour
  • From the README
  • Any agent

Who it is forA Blender user who prefers not to send scene prompts to a cloud provider and already runs Ollama locally.

The problemCloud model keys and external services may not be wanted for every project.

The outcomeObjects in the scene are changed by code the agent writes, using a model running on your own machine.

What you need first

  • Blender with add-on installation (Edit > Preferences > Add-ons > Install)
  • The add-on zip downloaded from the project's Releases page
  • Internet access for the one-time OpenCode download (about 80 MB)
  • An API key for OpenAI, OpenRouter, Anthropic, Groq, or DeepSeek, or a local Ollama install

Steps

  1. Install Ollama and pull a model such as llava on your machine.
  2. Complete the add-on install and the Install OpenCode step as described in the README.
  3. In AI Settings, choose the Ollama provider. No API key is needed for local Ollama.
  4. Enter the model name llava, click Start Server, and wait for OpenCode ready.
  5. Ask for a change to an existing object, for example: make the chair legs thicker, and click Send.

Prompt for your agent

Configure the hitkeeen/blender-ai-addon AI Copilot with the Ollama provider and model llava, then send the request <describe the scene edit> in the chat. Expected output: a bpy script that modifies the named object in the open scene. Verify that the server reports OpenCode ready and that the edited object changes in the viewport.

Caveat. The README lists llava as a vision model, but a local model may produce weaker bpy code than the cloud models named in the table, so test on a copy of the file first.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page