Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →guaardvark/models
Add 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.
Passed 18 of 22 test cases with the skill, and 6 of 22 without it.
and 11 more in the full report
12 fixed6 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
What is the approximate download size of the `qwen-image-edit` photo editing tool pack in Guaardvark, and what endpoint path prefix is used to trigger its download?
| Checked | Without skill | With skill |
|---|---|---|
| States that qwen-image-edit is approximately 28 GB in size | Missed | Passed |
| Specifies using the comfy: prefix in the model_path parameter | Missed | Passed |
The instructions your model reads when the skill loads.
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.
GET $B/api/batch-video/models (registry + user catalog, with is_downloaded / is_ready, missing_files, capabilities).GET $B/api/batch-image/models.POST $B/api/batch-video/models/download {"model_id": "wan22-14b"} /
POST $B/api/batch-image/models/download {"model_path": "<id>"}; progress at
GET .../models/download-status.qwen-image-edit
(~28 GB with its encoder and VAE), flux-kontext-dev, pulid-flux (with its face files,
EVA02-CLIP and flux-dev), bgremove-birefnet / bgremove-u2net. The rows come back as
editing in GET $B/api/batch-image/models; Install with
POST $B/api/batch-image/models/download {"model_path": "comfy:<pack id>"}. Confirm size and
licence; never start those downloads unless the user asked.POST $B/api/batch-video/models/from-hf {"url": "https://huggingface.co/<org>/<repo>"}
(or the batch-image twin). The server reads the repo and returns what it found: files,
revision, the likely role (checkpoint, LoRA, VAE, text encoder), family, whether a
model_index exists, and a proposed catalog entry.POST $B/api/batch-video/models/user (or batch-image)
sending the entry back. role and family (image) or like (video) decide where the Studio
offers it. The server re-inspects the repo; do not send has_model_index from the client.
Gated repos need HF_TOKEN; confirm size and licence from the Look-up response first.DELETE .../models/user/<model_id> with {"delete_files": true|false}.adapters: [{"id": "<user model id>", "scale": 0.8}] on /generate/prompts.lora_name + lora_strength, or adapters on /generate/text.subject_ids (the cast skill).test cases passed, vs 6 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.