Skip to content
Get packs

LoRA Space Builder

Builds and publishes a Gradio demo Space on Hugging Face for a LoRA model

Source Download skill
Repository
huggingface/skills
Stars
11,253
Licence
Apache-2.0
Files
8 files

What it does

When you ask, the agent reads a LoRA model's files and model card on the Hugging Face Hub, picks the matching base diffusion pipeline, and writes a small web app with a UI tailored to what that LoRA does. It then publishes that app as a Hugging Face Space, private by default, so you can try it in a browser. A LoRA is a small add-on file that changes how a larger image or video model behaves.

Great for

  • Creators who trained or host a LoRA on the Hub and want a shareable browser demo without writing web code
  • Developers who want a quick, model-card-faithful Gradio demo for a diffusion LoRA
  • Teams prototyping a playground for a LoRA before wider release

Skip it if

  • Users who only want to run a LoRA locally in a script, since this skill is built around publishing a Space; the publish step writes to your Hugging Face account using a write-scope token
  • Private or unreleased LoRAs where the user should not send weights or prompts to a public-facing demo without checking the privacy settings first
  • Tasks outside diffusion LoRAs, such as training a LoRA or general web apps, which this skill does not cover

Try asking

  • “Build and publish a Gradio Space for my Qwen-Image LoRA at username/my-lora”
  • “Make a playground for my LTX-Video motion LoRA and keep it private”
  • “Create a relighting demo Space for this portrait LoRA with the example images from its model card”
Step-by-step guide: how to use LoRA Space BuilderInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 8 original files, the Apache-2.0 licence and an attribution note.

    huggingface-lora-space-builder.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip huggingface-lora-space-builder.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip huggingface-lora-space-builder.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the LoRA repo ID (for example username/my-lora) and, if you know it, the task and what the LoRA does, to avoid follow-up questions
  • Keep the Space private until you have tested it, and review the generated app.py, requirements.txt and README before approving publication
  • Only paste a token into a session you trust, and revoke it afterwards if you no longer need it

What's inside

  • references/adapting-to-the-lora.md
  • references/base-models/krea-2.md
  • references/base-models/ltx.md
  • references/base-models/qwen-image.md
  • references/creative-mode.md
  • references/tasks.md
  • references/zerogpu-and-publishing.md
  • SKILL.md

Redistributed unmodified from huggingface/skills under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.