title: LoveBound AI Model Studio emoji: 💜 colorFrom: purple colorTo: blue sdk: gradio app_file: app.py pinned: false
LoveBound AI Model Studio v1.35.9 — Hugging Face Spaces FULL
This FULL package preserves the original plugin directory layout and all 24 original ZIP archives. It adds a Gradio Space app with read-only project ZIP diagnostics and a version/inventory panel.
Install on Hugging Face Spaces
- Create a private Gradio Space (recommended).
- Extract this archive locally. Upload all files and directories inside the archive to the Space repository root.
app.py,README.md, andrequirements.txtmust be at the root. - Large individual archives may require Git LFS / Xet-supported uploads; the Space build may exceed resource quotas. Never substitute a Git LFS pointer for the actual archive when offline preservation is required.
- Let the Space install
requirements.txtand startapp.py. - Use the read-only diagnostics tabs to inspect uploaded ZIPs.
What this does / does not do
- Includes original ChatGPT plugin manifests, scripts, configs, workspace templates and 24 source ZIPs, without deleting or repacking the source ZIP contents.
- Exposes the Hugging Face repository and dual-WebView inventory diagnostics as a Gradio UI.
- Does not automatically run a ChatGPT plugin in Spaces, execute GGUF models, fine-tune models, build EXE/APK, fix arbitrary source code, or deploy to GitHub/Cloudflare.
- Preserves the user-selected version
1.35.9as a project policy; this is not an immutable platform lock. - Security: Files committed to a public Space repository may be visible/downloadable. Audit licenses, private files, API keys, personal data and third-party code before uploading. Keep Space secrets in the Hugging Face Secrets settings, not in Git.
The assets/ directory contains third-party archives with their own licenses; their inclusion does not imply permission to redistribute publicly.
Training extension
MergeKit, LoRA, QLoRA and full fine-tuning launchers are under training/; see training/README.md. Space UI only generates plans. Install training dependencies and run on explicitly provisioned compatible GPU.