huggingface-lora-space-builder
Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored to the LoRA's task and inputs (Union/multi-task control, edit, video, image, etc.), respecting mode
Profile →npx skills add waybarrios/opencode-power-pack --skill huggingface-lora-space-builder --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
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, demo, Gradio app, or playground for a LoRA — whether the base model is Qwen-Image, Qwen-Image-Edit, LTX, or another diffusion model. Also use when someone describes a LoRA they trained or hosts on the Hub and wants to share it. 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.
How it works
Phase 1 — Gather LoRA info: Read the LoRA repo on the Hub, determine base model, task, trigger words, recommended inference parameters, and examples from the model card and README. If needed, prompt the user once for a write-access token and use huggingface_hub calls to list repo files and load the model card data.
Phase 2 — Pick the base pipeline: Load the appropriate base-model family reference file (qwen-image, ltx, or krea-2) and verify the pipeline class against the base model card's diffusers snippet. Decide between diffusers or a native pipeline depending on the base model card guidance.
Phase 3 — Design the UI for this LoRA: Design a UI tailored to the LoRA’s task and inputs, using the per-task patterns from references/tasks.md and the LoRA-specific considerations from references/adapting-to-the-lora.md. Include a self-check sentence describing the intended user action in 10 seconds. If necessary, propose creative UI elements or Gradio components and consider Hub custom components before going bespoke.
Phase 4 — Write the Space files: Produce app.py, requirements.txt, and README.md together and present all three for batch approval before publishing. Ensure the three files are coherent: module imports, constants (including LORA_REPO, BASE_MODEL, recommended steps, guidance, LoRA scale, trigger word), and module-level model loading with possible HF token handling. The workflow emphasizes a private Space on CUDA with a suitable @spaces.GPU duration and ZeroGPU-compatible configuration.
# Gradio LoRA Space Builder 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, or another diffusion model. Also use when someone describes a LoRA they traine
What does the huggingface-lora-space-builder skill do?
Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored to the LoRA's task and inputs (Union/multi-task control, edit, video, image, etc.), respecting mode
How do I install it?
Run `npx skills add waybarrios/opencode-power-pack --skill huggingface-lora-space-builder --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From waybarrios/opencode-power-pack, a repository with 443 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.