Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →guaardvark/video
Generate video clips on the user's own GPU through Guaardvark: text-to-video, image-to-video, first+last frame animation, clips with their own soundtrack and dialogue (MiniMax H3), short looping animations, and batch runs.
Passed 20 of 20 test cases with the skill, and 3 of 20 without it.
and 23 more in the full report
17 fixed3 passed either way0 still failing0 broke3 errored
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/14/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.
After a failed batch generation job with ID 'batch_98765', what exact REST endpoint and HTTP method should I call to retry the batch?
| Checked | Without skill | With skill |
|---|---|---|
| Uses POST /api/batch-video/retry/batch_98765 to retry the batch. | Missed | Passed |
The instructions your model reads when the skill loads.
Read setup first if the backend or the comfyui plugin state is unknown.
Video needs a 16 GB-class NVIDIA card. Clips take minutes, so every route is queued.
GET ${GUAARDVARK_URL:-http://localhost:5000}/api/batch-video/models lists the registry with
is_downloaded / is_ready (and missing_files), capabilities (modes t2v/i2v, max_frames, native_fps,
aspect_ratios, min_steps, speed_profiles, audio_out), vram_mb, size_gb, license. Installed on a typical box:
| id | what it is | notes |
|---|---|---|
wan22-5b | Wan 2.2 TI2V-5B, t2v + i2v, 24 fps, up to 121 frames | the everyday default |
wan22-14b / wan22-14b-i2v | Wan 2.2 14B MoE, 16 fps, 81 frames | best quality; speed_profile: lightx2v-4 for 4-step Lightning |
ltx23-distilled-fp8 | LTX-2.3 distilled, 8 steps, 161 frames | fastest long clips |
minimax-h3-int8 | MiniMax H3, text / first / last / first+last frame, generates its own stereo soundtrack and spoken lines | pass audio: true; ~6.5 min for 5 s on a 16 GB card |
cogvideox-5b / -i2v | CogVideoX, 8 fps, 49 frames | legacy |
The active default is GET /api/settings/active_video_model (resolved.t2v, resolved.i2v, resolved.scene).
Never pass a step count below the model's min_steps; the server raises it and the result would be smeared anyway.
generate_videoprompt: scene, subject, motion, style, and any spoken lines (H3 speaks them).model, duration_s (clamped to the model), aspect_ratio (one the model declares),
style (cinematic, realistic, anime, 3d_animation, ...), num_inference_steps, speed_profile.audio: true forces a soundtrack-capable model (H3) and fails on a silent family.first_image / last_image: document id or path; last frame needs a first+last mode model.reference_images (up to 9), reference_clips (up to 3, 2-15 s, their own sound left out) and
reference_audio (up to 3): lock a person, look, motion or voice on the reference build
(minimax-h3-ref2va-int8, picked when no model is named). The prompt names them
<Picture N>, <Video N>, <Audio N>; to keep a clip's sound, pass its track as
reference_audio. In the Studio this is the References input on Video Gen.wait_for_result default false: the tool returns a batch id and a Studio deep link at once.
Give the user the link; poll get_generation_status(batch_id=...) (MCP) or
GET /api/batch-video/status/<batch_id> if they ask you to wait. wait_for_result: true
blocks for the clip, up to 30 minutes.generate_animationtest cases passed, vs 3 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.