huggingface-lora-space-builder

name	huggingface-lora-space-builder
description	Publishes a Gradio Hugging Face Space that runs inference with a user-provided LoRA on ZeroGPU (diffusers pipelines for Qwen-Image, LTX, FLUX, SDXL, and similar). Use when the user wants a browser demo or playground for a LoRA. Not for training LoRAs, local Diffusers scripts (stable-diffusion), or ComfyUI graphs (comfyui).
version	1.0.1
risk	unknown
source	https://github.com/huggingface/skills/tree/main/skills/huggingface-lora-space-builder
source_repo	huggingface/skills
source_type	official
date_added	2026-07-01T00:00:00.000Z
license	Apache-2.0
license_source	https://github.com/huggingface/skills/blob/main/LICENSE

Gradio LoRA Space Builder

When to Use

Use this skill when you need to build and publish a Gradio demo on Hugging Face Spaces that runs inference with a user-provided LoRA. Use whenever someone asks to create, generate, ship, or publish "a Space", "a demo", "a Gradio app", or "a playground" for a LoRA — whether the base model is Qwen-Image, Qwen-Image-Edit, LTX, Wan, FLUX, SDXL, or another diffusion model. The default target is ZeroGPU hardware and the default inference library is diffusers when the base model supports it.

The output is a real, published Space (private by default) that the user can try in the browser, not a local script.

Prerequisites

• A Hugging Face account.
• A Hugging Face access token with write scope (to read the LoRA if it's private/gated, and to publish the Space). Create one at https://huggingface.co/settings/tokens.
• Python environment with huggingface_hub, gradio, and diffusers installed for local smoke-testing.

Procedure

Work through these phases in order. Information gathered in one phase decides the next. Don't drip-feed questions across multiple turns; batch them.

Phase 1: Gather LoRA Info

1. Check for cached token first. Do not immediately ask for a token. Check if the user is already authenticated.

   from huggingface_hub import HfApi, get_token
   
   cached_token = get_token()  # picks up HF_TOKEN env var or cached CLI login
   if cached_token:
       try:
           info = HfApi().whoami(token=cached_token)
           username = info["name"]
       except Exception:
           cached_token = None  # token exists but is invalid/expired
   

2. Ask for token only if needed. If no cached token exists or it can't read a private repo, ask once: "I need a Hugging Face access token with write scope (to read the LoRA if it's private/gated, and to publish the Space). Create one at https://huggingface.co/settings/tokens. Paste it here."
3. Read the LoRA repo. List files (HfApi().list_repo_files(repo_id)) and fetch the model card (ModelCard.load(repo_id)).