DEDUPEDWho it is forA designer or developer who wants to modify existing images rather than generate from scratch.
The problemEach editing technique comes from a different paper and repo, each with its own setup.
The outcomeEdited, inpainted or upscaled images from the same library and loading pattern.
What you need first
- Python in a virtual environment
- PyTorch; install with `pip install --upgrade diffusers[torch]` or conda
- An NVIDIA GPU for the README examples, which call to cuda; Apple Silicon has its own guide
Steps
- Install with
pip install --upgrade diffusers[torch] - Pick the task from the Popular Tasks and Pipelines table, such as Text-guided Image Inpainting or Super Resolution
- Load the matching checkpoint from the table, for example stable-diffusion-v1-5/stable-diffusion-inpainting or stabilityai/stable-diffusion-x4-upscaler
- Pass your input image and prompt to the pipeline
- Use the Optimization guides to cut memory use if the pipeline does not fit on your GPU
Prompt for your agent
With huggingface/diffusers, build a small tool that takes <input image> and either upscales it with the Stable Diffusion x4 upscaler or inpaints a masked area with the inpainting checkpoint, depending on a command line flag. Save outputs next to the input.
Caveat. Each pipeline takes slightly different inputs, so check its docs page for the exact arguments.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for huggingface/diffusers and "Edit, inpaint or upscale images with ready-made pipelines"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer