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...
Profile →npx skills add sickn33/agentic-awesome-skills --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.
How it works
- Gather LoRA info from a Hub repo: read repo files, fetch the model card, determine base model, task, trigger words, and recommended inference parameters. If the repo is private, request a one-time Hugging Face token with write scope. 2) Pick the base pipeline by loading a reference file for the base model family (qwen-image.md, ltx.md, or krea-2.md) and verify against the base model card’s diffusers snippet to decide the pipeline class. 3) Design a UI for the LoRA based on task guidance and the LoRA-specific needs described in adapting-to-the-lora.md, ensuring the UI is purpose-built rather than template-driven. 4) Write the three Space files together: app.py, requirements.txt, and README.md, and present all three to the user for batch approval before publishing. 5) Publish the Space (private) per ZeroGPU rules, including module-level CUDA placement, appropriate GPU duration, and inference function decoration. 6) In app.py, include Imports, Constants (LORA_REPO, BASE_MODEL, recommended step count, guidance, LoRA scale, trigger word), and a pipeline load with load_lora_weights; place the model on CUDA at module level. A single batched review is shown for approval before publishing.
# Gradio LoRA Space Builder ## When to Use Use this skill when you need 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... 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 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. ## What "good" looks like for these demos The demo should feel handcrafted for this specific LoRA, not a generic template with the LoRA bolted on. Two LoRAs that share a task can still need
- When to Use
- What "good" looks like for these demos
- Workflow
- Phase 1 — Gather LoRA info
- Phase 2 — Pick the base pipeline
- Phase 3 — Design the UI for this LoRA
- Phase 4 — Write the Space files
- app.py
- requirements.txt
- README.md
- Single batched approval — order of operations matters
- Phase 5 — Publish the Space
- Phase 6 — Smoke-test the Space
- What to avoid
gradio predict {repo_id} /predict '{"prompt": "...", "aspect_ratio": "1:1", ...}' --token $HF_TOKEN
Image-to-image (file input):
gradio predict {repo_id} /predict '{"input_image": {"path": "/tmp/sample.jpg", "meta": {"_type": "gradio.FileData"}}, "prompt": "..."}' --token $HF_TOKENWhat 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...
How do I install it?
Run `npx skills add sickn33/agentic-awesome-skills --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 sickn33/agentic-awesome-skills, a repository with 44,414 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.