Models and LoRAs with Guaardvark
SkillMediaAdd any Hugging Face image or video model, checkpoint or LoRA to Guaardvark from a URL, list what is installed, and download registry models on request. Use when the user pastes a huggingface.co link or a .safetensors URL, asks "can it run <model>", or wants a new LoRA or checkpoint available in the Studio.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Models and LoRAs with Guaardvark skill
What this skill tells your AI
The instructions your AI receives, as published by guaardvark/guaardvark in .agents/skills/models/SKILL.md and read by ahel’s review.
B=${GUAARDVARK_URL:-http://localhost:5000}. Nothing downloads without an explicit Install;
the product never phones home on its own. Always confirm the size and the licence with the user first.
What is there
- Video:
GET $B/api/batch-video/models(registry + user catalog, withis_downloaded/is_ready,missing_files,capabilities). - Image:
GET $B/api/batch-image/models. - Download a registry model:
POST $B/api/batch-video/models/download {"model_id": "wan22-14b"}/POST $B/api/batch-image/models/download {"model_path": "<id>"}; progress atGET .../models/download-status.
Add from a Hugging Face URL (the "paste a link" path)
- Inspect:
POST $B/api/batch-video/models/from-hf {"url": "https://huggingface.co/<org>/<repo>"}(or thebatch-imagetwin). The server reads the repo and returns what it found: files, revision, the likelyrole(checkpoint, LoRA, VAE, text encoder),family, whether amodel_indexexists, and a proposed catalog entry. - Show that to the user: which file(s), role, family, size, licence.
- Register (and optionally install) with
POST $B/api/batch-video/models/user(orbatch-image) sending the entry back, e.g.{"url": "...", "hf_repo": "org/repo", "revision": "main", "files": ["model.safetensors"], "role": "lora", "family": "wan22", "name": "My LoRA", "description": "...", "install": true}roleandfamilydecide where the Studio offers it (a Wan LoRA appears under Wan models; an SDXL checkpoint under image models). Video entries also takelike: "<registry id>"to inherit that model's capabilities. - Remove:
DELETE .../models/user/<model_id>with{"delete_files": true|false}.
Using a user LoRA
- Batch image:
adapters: [{"id": "<user model id>", "scale": 0.8}]on/generate/prompts. - Batch video:
lora_name+lora_strength, oradapterson/generate/text. - A trained Cast LoRA is different: it rides on
subject_ids(the cast skill).
Rules
- A direct
.safetensorsURL works when it lives on huggingface.co; the inspector needs the repo to read the file list. For other hosts, ask the user to download the file and drop it in the Studio's model folder instead. - Declared limits (min steps, max frames) come from the registry entry; a user model inherits
them from
like/family. Do not invent numbers for a model the registry does not know.
Signals
- GitHub stars
- 211
- Forks
- 45
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
models- Source
- github.com/guaardvark/guaardvark