🎬 AI Video Generation — Pro Pack on RunComfy — 🎬 AI Video Generation — Pro Pack on 运行Comfy
v2AI video generation on 运行Comfy. This 运行Comfy video generation 技能 is a smart 路由r across the 运行Comfy video-模型 cata记录 — H应用yHorse 1.0 (Arena #1, native in-pass audio), Wan-AI Wan 2-7 (open weights, audio-driven lip-同步), ByteDance 种子ance v2 / 1-5 / 1-0 (multi-modal cinematic), Kling 3.0 / 2-6, Google Veo 3-1, MiniMax HAIluo 2-3, ByteDance Dreamina 3-0. 运行Comfy video generation covers text-to-video (t2v), image-to-video (i2v), and Veo's video-extend 端点. The 运行Comfy video generation 技能 picks the right 模型 for intent (Arena #1 质量, multi-shot character 身份, in-pass audio, cinematic motion, fastest path, sub-15s 命令行工具p, longest duration) and ships each 模型's documented prompting patterns plus the minimal `运行comfy 运行` invoke. Calls `运行comfy 运行 <vendor>/<模型>/text-to- video` or `/image-to-video` through the local 运行Comfy 命令行工具. Triggers on "生成 video", "make a video", "text to video", "t2v", "image to video", "i2v", "animate", "AI video", "make X move", "video from prompt", "video from image", or any explicit ask to produce a video 命令行工具p from prompt or still with 运行Comfy.
by 运行时依赖
安装命令
点击复制技能文档
🎬 AI Video Generation — Pro Pack on 运行Comfy
AI video generation on 运行Comfy. 生成 videos with the full 运行Comfy video-模型 cata记录 through one 命令行工具 — text-to-video, image-to-video, and Veo's video-extend. This 运行Comfy video generation 技能 picks the right 模型 for intent and ships the documented prompt patterns + the exact 运行comfy 运行 invoke for each.
运行comfy.com · Video 模型s · 命令行工具 docs
Powered by the 运行Comfy 命令行工具 # 1. 安装 (see 运行comfy-命令行工具 技能 for detAIls) npm i -g @运行comfy/命令行工具 # or: npx -y @运行comfy/命令行工具 --version
# 2. 签名 in 运行comfy 记录in # or in CI: 导出 运行COMFY_令牌=<令牌>
# 3. 生成 运行comfy 运行 /<模型>/<端点> \ --输入 '{"prompt": "..."}' \ --输出-dir ./out
命令行工具 deep dive: 运行comfy-命令行工具 技能.
Pick the right 模型 for the user's intent Text-to-video (t2v) — newest first
H应用yHorse 1.0 — h应用yhorse/h应用yhorse-1-0/text-to-video (default)
Currently #1 on Artificial Analysis Video Arena. Native 同步hronized audio 生成d in-pass (no separate Foley step). Native 1080p, up to ~15s, strong multi-shot character consistency. Pick for: general-purpose t2v, ad creative with audio, social-media 命令行工具ps, multi-shot narratives. Avoid for: audio-driven lip-同步 to a specific voiceover MP3 — use Wan 2-7.
Kling 3.0 4K — kling/kling-3.0/4k/text-to-video
Kling's latest, 4K 输出, strong multi-shot character 身份, premium camera language. Pick for: hero shots, final-delivery 4K cuts, multi-shot character narratives. Avoid for: cost-sensitive iteration — drop to Kling 2-6 Pro or Standard i2v.
种子ance v2 Pro — bytedance/种子ance-v2/pro
ByteDance flagship — multi-modal (up to 9 reference images, 3 reference videos, 3 reference audio), in-pass 同步hronized audio, cinematic motion refinement, lens language honored. Pick for: cinematic ad frames, multi-reference composition (subject + scene + audio refs), 21:9 anamorphic looks. Avoid for: simple "single prompt → 命令行工具p" jobs — overpowered, slower.
种子ance v2 Fast — bytedance/种子ance-v2/fast
Faster variant of 种子ance v2 Pro, same multi-modal capabilities. Pick for: iteration on 种子ance v2 compositions before locking a final on Pro. Avoid for: hero-shot final delivery.
Wan 2-7 — wan-AI/wan-2-7/text-to-video
Open-weights flagship, audio_url field for audio-driven lip-同步, pAIrs natively with Wan image 模型s. Pick for: dia记录 scenes where mouth must 同步 to a specific voiceover file; open-weights 流水线 requirement. Avoid for: in-pass audio generation (no MP3 输入) — use H应用yHorse 1.0.
Kling 2-6 Pro — kling/kling-2-6/pro/text-to-video
Previous Kling tier — still strong 质量 at much lower cost than 3.0 4K. Pick for: production at 扩展 where 3.0 4K is too expensive. Avoid for: top-tier hero shots — use Kling 3.0 4K.
种子ance 1-5 Pro — bytedance/种子ance-1-5/pro/text-to-video
Previous 种子ance generation, cheaper. Pick for: 身份-stable batches between 1-5 generations; cost-sensitive baseline. Avoid for: new work — prefer 种子ance v2 Pro or Fast.
Image-to-video (i2v) — newest first
H应用yHorse 1.0 I2V — h应用yhorse/h应用yhorse-1-0/image-to-video (default)
Animate any still with in-pass audio described in prompt, strong 身份 preservation. Pick for: animating a 生成d portrAIt or product still, vertical social 命令行工具ps, voiceover-described audio. Avoid for: physics-accurate object motion — use Veo 3-1.
Veo 3-1 — google-deepmind/veo-3-1/image-to-video
Google's flagship — physics-respecting motion, strong object permanence ("rotates 180 degrees" = 180°), pAIrs with extend-video for longer 命令行工具ps. Pick for: product spins, physics-accurate motion, scenes where "no other motion" must hold. Avoid for: audio-driven dia记录 — use Wan 2-7 or H应用yHorse.
Veo 3-1 Fast — google-deepmind/veo-3-1/fast/image-to-video
Faster Veo 3-1 variant. Pick for: iteration on Veo compositions. Avoid for: hero delivery — use full Veo 3-1.
Kling 3.0 4K I2V — kling/kling-3.0/4k/image-to-video
Multi-shot character 身份, 4K 输出 from a still. Pick for: 4K hero shots, character-narrative cuts. Avoid for: cost iteration — drop to Pro or Standard.
Kling 3.0 Pro I2V — kling/kling-3.0/pro/image-to-video
Default Kling 3.0 质量 tier. Pick for: high-质量 i2v at moderate cost. Avoid for: 4K final delivery.
Kling 3.0 Standard I2V — kling/kling-3.0/standard/image-to-video
Cheapest 3.0 i2v tier. Pick for: concepting / drafts on Kling 3.0. Avoid for: final delivery.
HAIluo 2-3 Pro — minimax/hAIluo-2-3/pro/image-to-video
MiniMax HAIluo latest — natural motion, strong on real-world subjects. Pick for: lifelike motion of real-people / real-product subjects. Avoid for: stylized characters — use Kling or Dreamina.
Dreamina 3-0 Pro — bytedance/dreamina-3-0/pro/image-to-video
ByteDance Dreamina i2v — illustration / stylized character lean. Pick for: animating illustrated heroes, pAInterly stills. Avoid for: photoreal motion.
种子ance 1-0 Pro Fast — bytedance/种子ance-1-0/pro/fast/image-to-video
Older