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. Use when the user asks to make, render, animate, or batch-generate video locally.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
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_animationFrame-morph GIF/MP4 via img2img: prompt, motion, frames 2-24, strength 0.1-0.5, format gif|mp4|both.
Use for short loops and stickers, not for cinema clips. Over MCP it answers at once with a job id
(tooljob_...); poll get_generation_status for the GIF and MP4 URLs, or pass
wait_for_result: true to wait up to 60 s for them.
B=${GUAARDVARK_URL:-http://localhost:5000}
# text to video, one clip per prompt
curl -s -X POST $B/api/batch-video/generate/text -H 'Content-Type: application/json' -d '{
"prompts": ["a red kite over a grey sea", "the same kite at dusk"],
"model": "wan22-5b", "prompt_style": "cinematic", "enhance_prompt": true, "seed": 42
}'
# image to video
curl -s -X POST $B/api/batch-video/generate/image -H 'Content-Type: application/json' -d '{
"image_paths": ["/abs/path/frame.png"], "prompt": "slow push in, wind in the grass", "model": "wan22-5b"
}'
Optional keys the server honours: negative_prompt, guidance_scale, motion_strength,
interpolation_multiplier (RIFE frame interpolation), combine_frames, lora_name +
lora_strength, adapters, guides (per-prompt audio/image anchors on models that declare them),
last_frame_paths (image route), storyboard_concept / storyboard_shots.
Poll GET $B/api/batch-video/status/<batch_id>; files via
GET $B/api/batch-video/video/<batch_id>/<video_name>; cancel POST $B/api/batch-video/batch/<batch_id>/cancel;
retry POST $B/api/batch-video/retry/<batch_id>.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Build consistent characters, environments and props in Guaardvark's Cast Library and train LoRAs for them locally (reference photos → vision bible → sample plan → approved samples → training). Use when the user wants the same face or object across images, videos, a music video, or a Film Crew production, or asks to "train a LoRA".
中文简介正在准备中。当前显示原文说明。
Code intelligence over repositories Guaardvark has indexed: semantic code search, exact-text search, file listing, PageRank repository map, import dependency graph, reading one class or function, analysis and generated rewrites, plus the System Mapper and self-improvement status. Use when the user asks where something is implemented, how modules depend on each other, or wants an architecture map of an indexed repo.
中文简介正在准备中。当前显示原文说明。
Run Guaardvark's five-role Film Crew locally: screenwriter, casting (Cast Library LoRAs), cinematographer storyboards, keyframe renders, editor. Turns a logline or screenplay into a finished short video with human gates at casting and storyboard. Use when the user says "film this", "make a short film", "storyboard this script", or "start the film crew".
中文简介正在准备中。当前显示原文说明。
Generate or edit images on the user's own GPU through Guaardvark: single images, instruction edits, background cut-outs, inpaint and outpaint, consistent characters from the Cast Library, and batch runs of many prompts. Use when the user asks to create, draw, render, visualize, edit, or batch-generate images locally.
中文简介正在准备中。当前显示原文说明。
Answer from the user's own indexed documents with Guaardvark's local RAG, browse and read indexed files section by section, remember facts across sessions, and process or fetch new material. Use when the user asks what their documents say, wants a source-cited answer from their files, says "remember this", or asks to index a PDF, DOCX, spreadsheet, image or URL.
中文简介正在准备中。当前显示原文说明。
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. 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.
中文简介正在准备中。当前显示原文说明。