安装 belt CLI 技能:
npx skills add belt-sh/cli
图像转视频
通过 inference.sh CLI 将静态图像转换为动画视频。
快速开始
需要 inference.sh CLI(
belt)。安装说明
belt login
# 生成静态图像
belt app run falai/flux-dev-lora --input '{
"prompt": "serene mountain lake at sunset, snow-capped peaks reflected in still water, golden hour light, landscape photography",
"width": 1248,
"height": 832
}'
# 将其动画化
belt app run falai/wan-2-5-i2v --input '{
"prompt": "gentle ripples on the lake surface, clouds slowly drifting, warm light shifting, birds flying in the distance",
"image": "path/to/lake-image.png"
}'
模型选择
| 模型 | 应用 ID | 最佳用途 | 运动风格 |
|---|---|---|---|
| Wan 2.5 i2v | falai/wan-2-5-i2v | 逼真运动,自然移动 | 摄影写实,细微 |
| WAN-I2V (Pruna) | pruna/wan-i2v | 经济实惠,快速,480p/720p | 自然,高效 |
| Seedance 2.0 | bytedance/seedance-2-0 | 高达 1080p,同步音频,所有输入类型 | 多用途,高质量 |
| Seedance 2.0 Fast | bytedance/seedance-2-0-fast | 快速变体,相同功能 | 多用途,快速 |
| Fabric 1.0 | falai/fabric-1-0 | 布料、织物、液体、流动材质 | 基于物理的流动 |
| Grok Imagine Video | xai/grok-imagine-video | 通用动画,文本引导 | 多用途 |
何时使用每种模型
| 场景 | 最佳模型 | 原因 |
|---|---|---|
| 带有水/云的风景 | Wan 2.5 i2v | 自然逼真运动的最佳选择 |
| 带有细微表情的人像 | Wan 2.5 i2v | 保持面部保真度 |
| 带有织物/布料的产品 | Fabric 1.0 | 专精于材质物理 |
| 旗帜飘扬,窗帘飘动 | Fabric 1.0 | 布料模拟 |
| 插画/艺术图像 | Seedance 2.0 | 匹配风格化内容 |
| 通用“赋予生命” | Seedance 2.0 | 出色的全能型,高达 1080p |
| 快速测试/迭代 | Seedance 2.0 Fast | 生成速度更快 |
运动类型
相机运动
| 运动 | 提示关键词 | 效果 |
|---|---|---|
| 推近 / 向前推轨 | "slow dolly forward", "camera pushes in" | 增强亲密感/聚焦 |
| 拉远 / 向后拉轨 | "camera pulls back", "slow zoom out" | 揭示,展示上下文 |
| 左右摇移 | "camera pans slowly to the right" | 扫描,跟随 |
| 上下俯仰 | "camera tilts upward" | 揭示高度 |
| 环绕 | "camera orbits around the subject" | 3D 探索 |
| 升降 | "camera rises upward" | 宏大展示 |
| 静态 | (无相机运动提示) | 仅主体运动 |
主体运动
| 类型 | 提示示例 |
|---|---|
| 自然元素 | "water rippling", "clouds drifting", "leaves rustling in breeze" |
| 头发/衣物 | "hair blowing gently in wind", "dress fabric flowing" |
| 氛围 | "fog slowly rolling", "dust particles floating in light beams" |
| 角色 | "person slowly turns to camera", "subtle breathing motion" |
| 机械 | "gears turning", "clock hands moving" |
| 液体 | "coffee steam rising", "paint dripping", "water pouring" |
提示编写最佳实践
黄金法则:细微 > 剧烈
AI 视频模型在柔和、细微的运动上效果更好,而非剧烈动作。请求过多运动会导致失真和伪影。
❌ "person running and jumping over obstacles while the camera spins"
✅ "person slowly walking forward, gentle breeze, camera follows alongside"
❌ "explosion with debris flying everywhere"
✅ "candle flame flickering gently, warm ambient light shifting"
❌ "fast zoom into the eyes with dramatic camera shake"
✅ "slow dolly forward toward the subject, subtle focus shift"
提示结构
[相机运动] + [主体运动] + [氛围效果] + [情绪/节奏]
各场景示例
# 风景动画
belt app run falai/wan-2-5-i2v --input '{
"prompt": "gentle camera pan right, water reflecting moving clouds, trees swaying slightly in breeze, warm golden light, peaceful and slow",
"image": "landscape.png"
}'
# 人像动画
belt app run falai/wan-2-5-i2v --input '{
"prompt": "subtle breathing motion, slight head turn, natural eye blink, hair moving gently, soft ambient lighting shifts",
"image": "portrait.png"
}'
# 产品展示动画
belt app run bytedance/seedance-2-0 --input '{
"prompt": "slow 360 degree orbit around the product, gentle spotlight movement, subtle reflections shifting, premium product showcase, smooth motion",
"image": "product.png",
"generate_audio": true
}'
# 织物/布料动画
belt app run falai/fabric-1-0 --input '{
"prompt": "fabric flowing and rippling in gentle wind, natural cloth physics, soft movement",
"image": "fabric-scene.png"
}'
# 建筑可视化
belt app run falai/wan-2-5-i2v --input '{
"prompt": "slow dolly forward through the entrance, slight camera tilt upward, ambient light filtering through windows, dust particles in light beams",
"image": "building-interior.png"
}'
时长建议
| 时长 | 质量 | 用途 |
|---|---|---|
| 2-3 秒 | 最高质量 | GIF、循环背景、动图 |
| 4-5 秒 | 高质量 | 社交媒体帖子、产品展示 |
| 6-8 秒 | 好质量 | 短片、过渡 |
| 10+ 秒 | 质量下降 | 避免使用,除非拼接短视频 |
延长时长
如需更长的视频,生成多个短视频片段并拼接:
# 从同一图像生成 3 个片段,使用渐进式运动
belt app run falai/wan-2-5-i2v --input '{
"prompt": "slow pan left, gentle water motion",
"image": "scene.png"
}' --no-wait
belt app run falai/wan-2-5-i2v --input '{
"prompt": "continuing pan, clouds shifting, light changing",
"image": "scene.png"
}' --no-wait
# 拼接在一起
belt app run infsh/media-merger --input '{
"media": ["clip1.mp4", "clip2.mp4"]
}'
完整工作流
静态图像到最终视频的流水线
# 1. 生成源图像(最佳质量)
belt app run bytedance/seedream-4-5 --input '{
"prompt": "cinematic landscape, misty mountains at dawn, lake in foreground, dramatic clouds, golden hour, 4K quality, professional photography",
"size": "2K"
}'
# 2. 将图像动画化
belt app run falai/wan-2-5-i2v --input '{
"prompt": "gentle mist rolling through the valley, lake surface rippling, clouds slowly moving, birds in distance, warm light shifting",
"image": "landscape.png"
}'
# 3. 如有需要,放大视频
belt app run falai/topaz-video-upscaler --input '{
"video": "animated-landscape.mp4"
}'
# 4. 添加环境音效
belt app run infsh/hunyuanvideo-foley --input '{
"video": "animated-landscape.mp4",
"prompt": "gentle nature ambience, distant birds, soft wind, water lapping"
}'
# 5. 合并视频和音频
belt app run infsh/video-audio-merger --input '{
"video": "upscaled-landscape.mp4",
"audio": "ambient-audio.mp3"
}'
Cinemagraph 效果
Cinemagraph 是一种只有特定元素移动的静态照片(例如,在静止场景中只有瀑布流动)。实现方法:
- 生成静态图像时明确定义运动元素
- 提示仅在该特定元素中运动
- 保持 2-4 秒以实现无缝循环
belt app run falai/wan-2-5-i2v --input '{
"prompt": "only the waterfall is moving, everything else remains perfectly still, water cascading smoothly, rest of scene frozen",
"image": "waterfall-scene.png"
}'
常见错误
| 错误 | 问题 | 解决方法 |
|---|---|---|
| 请求过多运动 | 失真、伪影、扭曲 | 始终遵循细微 > 剧烈 |
| 模型与内容类型不匹配 | 效果不佳 | 使用上方选择指南 |
| 片段过长(10 秒以上) | 质量显著下降 | 保持在 3-5 秒,必要时拼接 |
| 未指定相机运动 | 随机/不可预测的运动 | 始终指定相机行为 |
| 运动方向冲突 | 混乱、不自然 | 只指定一个主要运动方向 |
| 源图像分辨率低 | 视频输出分辨率低 | 从最高质量的源图像开始 |
| 复杂的动作场景 | 模型无法处理 | 保持运动简单自然 |
相关技能
npx skills add inference-sh/skills@ai-video-generation
npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@p-video
npx skills add inference-sh/skills@video-prompting-guide
npx skills add inference-sh/skills@prompt-engineering
浏览所有应用:belt app list