← 返回 Skills 市场
okaris

Image To Video

作者 Ömer Karışman · GitHub ↗ · v0.1.5
cross-platform ⚠ suspicious
1273
总下载
0
收藏
12
当前安装
1
版本数
在 OpenClaw 中安装
/install image-to-video
功能描述
Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use ea...
使用说明 (SKILL.md)

Image to Video

Convert still images to animated videos via inference.sh CLI.

Quick Start

curl -fsSL https://cli.inference.sh | sh && infsh login

# Generate a still image
infsh 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
}'

# Animate it
infsh 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"
}'

Install note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.

Model Selection

Model App ID Best For Motion Style
Wan 2.5 i2v falai/wan-2-5-i2v Realistic motion, natural movement Photorealistic, subtle
Seedance 1.5 Pro bytedance/seedance-1-5-pro Stylized, creative, animation-like Artistic, expressive
Seedance 1.0 Pro bytedance/seedance-1-0-pro General purpose, good quality Balanced
Fabric 1.0 falai/fabric-1-0 Cloth, fabric, liquid, flowing materials Physics-based flow
Grok Imagine Video xai/grok-imagine-video General animation, text-guided Versatile

When to Use Each

Scenario Best Model Why
Landscape with water/clouds Wan 2.5 i2v Best at natural, realistic motion
Portrait with subtle expression Wan 2.5 i2v Maintains face fidelity
Product with fabric/cloth Fabric 1.0 Specialized in material physics
Flag waving, curtain flowing Fabric 1.0 Cloth simulation
Illustrated/artistic image Seedance Matches stylized content
General "bring to life" Seedance 1.5 Pro Good all-rounder
Quick test/iteration Seedance 1.0 Lite Fastest, 720p

Motion Types

Camera Movement

Movement Prompt Keyword Effect
Push in / Dolly forward "slow dolly forward", "camera pushes in" Increasing intimacy/focus
Pull out / Dolly back "camera pulls back", "slow zoom out" Reveal, context
Pan left/right "camera pans slowly to the right" Scanning, following
Tilt up/down "camera tilts upward" Revealing height
Orbit "camera orbits around the subject" 3D exploration
Crane up "camera rises upward" Grand reveal
Static (no camera movement prompt) Subject motion only

Subject Motion

Type Prompt Examples
Natural elements "water rippling", "clouds drifting", "leaves rustling in breeze"
Hair/clothing "hair blowing gently in wind", "dress fabric flowing"
Atmospheric "fog slowly rolling", "dust particles floating in light beams"
Character "person slowly turns to camera", "subtle breathing motion"
Mechanical "gears turning", "clock hands moving"
Liquid "coffee steam rising", "paint dripping", "water pouring"

Prompting Best Practices

The Golden Rule: Subtle > Dramatic

AI video models produce better results with gentle, subtle motion than dramatic action. Requesting too much movement causes distortion and artifacts.

❌ "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"

Prompt Structure

[Camera movement] + [Subject motion] + [Atmospheric effects] + [Mood/pace]

Examples by Scenario

# Landscape animation
infsh 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"
}'

# Portrait animation
infsh 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"
}'

# Product shot animation
infsh app run bytedance/seedance-1-5-pro --input '{
  "prompt": "slow 360 degree orbit around the product, gentle spotlight movement, subtle reflections shifting, premium product showcase, smooth motion",
  "image": "product.png"
}'

# Fabric/cloth animation
infsh app run falai/fabric-1-0 --input '{
  "prompt": "fabric flowing and rippling in gentle wind, natural cloth physics, soft movement",
  "image": "fabric-scene.png"
}'

# Architectural visualization
infsh 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"
}'

Duration Guidelines

Duration Quality Use For
2-3 seconds Highest quality GIFs, looping backgrounds, cinemagraphs
4-5 seconds High quality Social media posts, product reveals
6-8 seconds Good quality Short clips, transitions
10+ seconds Quality degrades Avoid unless stitching shorter clips

Extending Duration

For longer videos, generate multiple short clips and stitch:

# Generate 3 clips from the same image with progressive motion
infsh app run falai/wan-2-5-i2v --input '{
  "prompt": "slow pan left, gentle water motion",
  "image": "scene.png"
}' --no-wait

infsh app run falai/wan-2-5-i2v --input '{
  "prompt": "continuing pan, clouds shifting, light changing",
  "image": "scene.png"
}' --no-wait

# Stitch together
infsh app run infsh/media-merger --input '{
  "media": ["clip1.mp4", "clip2.mp4"]
}'

The Full Workflow

Still-to-Final-Video Pipeline

# 1. Generate source image (best quality)
infsh 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. Animate the image
infsh 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. Upscale video if needed
infsh app run falai/topaz-video-upscaler --input '{
  "video": "animated-landscape.mp4"
}'

# 4. Add ambient audio
infsh app run infsh/hunyuanvideo-foley --input '{
  "video": "animated-landscape.mp4",
  "prompt": "gentle nature ambience, distant birds, soft wind, water lapping"
}'

# 5. Merge video with audio
infsh app run infsh/video-audio-merger --input '{
  "video": "upscaled-landscape.mp4",
  "audio": "ambient-audio.mp3"
}'

Cinemagraph Effect

A cinemagraph is a still photo where only one element moves (e.g., waterfall moving in an otherwise frozen scene). To achieve this:

  1. Generate the still image with the motion element clearly defined
  2. Prompt for motion only in that specific element
  3. Keep to 2-4 seconds for seamless looping
infsh 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"
}'

Common Mistakes

Mistake Problem Fix
Too much motion requested Distortion, artifacts, warping Subtle > dramatic, always
Wrong model for content type Poor results Use selection guide above
Clips too long (10s+) Quality degrades significantly Keep to 3-5 seconds, stitch if needed
No camera movement specified Random/unpredictable motion Always specify camera behavior
Conflicting motion directions Chaotic, unnatural One primary motion direction
Low-res source image Low-res video output Start with highest quality source
Complex action scenes Models can't handle Keep motion simple and natural

Related Skills

npx skills add inference-sh/skills@ai-video-generation
npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@video-prompting-guide
npx skills add inference-sh/skills@prompt-engineering

Browse all apps: infsh app list

安全使用建议
This skill is a plausible and useful how-to for animating images, but it relies on a third‑party CLI (infsh) installed by piping a remote script into sh — a risky pattern. Before installing or running it: (1) avoid running curl | sh blind; prefer downloading the installer and verifying the SHA‑256 checksum yourself against the published checksums URL, (2) inspect the install script (and any binary) or run it in a sandbox/VM, (3) assume infsh will upload images and require an account/login — do not use sensitive or private images until you confirm the provider's privacy/policy, (4) ask the skill author for source/homepage or a reproducible manual install path and explicit details about what data is sent, and (5) if you need strong privacy, prefer local/offline tools or self‑hosted inference rather than an unknown remote provider. If the author can provide a verified release URL, reproducible install steps, and an explicit disclosure about authentication and data upload, this would reduce the risk.
功能分析
Type: OpenClaw Skill Name: image-to-video Version: 0.1.5 The skill is classified as suspicious due to the use of `curl -fsSL ... | sh` for installation, which is a high-risk supply chain vulnerability allowing arbitrary code execution if the remote script (`cli.inference.sh`) is compromised. Additionally, the `allowed-tools: Bash(infsh *)` permission is overly broad, granting the agent the ability to execute any command via the `infsh` tool, which could be exploited if `infsh` itself has vulnerabilities or is misused. While the stated purpose is benign, these capabilities introduce significant security risks.
能力评估
Purpose & Capability
The name/description match the SKILL.md content: it is a how-to for animating images and lists concrete model app IDs. However, the runtime instructions depend on an external CLI (infsh) even though the registry declares no required binaries; that dependency is implicit rather than declared.
Instruction Scope
Runtime instructions tell the agent to download/run a remote install script (curl https://cli.inference.sh | sh) and then run infsh app run ... and infsh login. The SKILL.md does not explicitly warn that running model inference will likely upload images to a remote provider, nor does it explain what credentials or data are sent. The instructions therefore expand scope beyond simple local guidance into remote execution and potential data transfer without declaring that behavior.
Install Mechanism
Although the doc claims the installer verifies SHA-256 and provides a checksums URL, the Quick Start recommends piping the remote install script directly into sh (curl | sh), which bypasses manual verification and is a high‑risk install pattern. The install source is a third‑party domain (inference.sh / dist.inference.sh) rather than a clearly established package registry; this elevates risk compared with no install or packaged installs.
Credentials
The registry lists no required environment variables or credentials, yet the instructions call out 'infsh login' (implying credentials) and will likely send local image files to a remote inference service. This is an incoherence: the skill implicitly requires account/authentication and network access but the metadata does not declare or justify any credentials or data-flow implications.
Persistence & Privilege
always:false and no code files in the skill means it does not demand platform-level persistent privileges. However, the recommended install writes a third‑party binary (infsh) to the system, creating a persistent CLI that the agent (or user) can invoke later — a modest persistence footprint that the skill does not disclose in registry metadata.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install image-to-video
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /image-to-video 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.1.5
image-to-video 0.1.5 - Major documentation update: now includes a comprehensive conversion guide on model selection, motion prompting, and camera movement for animating still images into video. - Added detailed tables summarizing available models (Wan 2.5 i2v, Seedance, Fabric, Grok Video), their strengths, and recommended use cases. - Expanded motion prompting section with clear examples for both camera and subject movement. - Introduced best practices for animation prompts, including practical do's and don'ts. - Clarified workflow steps and provided bash command examples for generating, animating, and enhancing videos from still images. - Included a new section on optimal video durations and how to extend videos by stitching multiple short clips.
元数据
Slug image-to-video
版本 0.1.5
许可证
累计安装 14
当前安装数 12
历史版本数 1
常见问题

Image To Video 是什么?

Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use ea... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1273 次。

如何安装 Image To Video?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install image-to-video」即可一键安装,无需额外配置。

Image To Video 是免费的吗?

是的,Image To Video 完全免费(开源免费),可自由下载、安装和使用。

Image To Video 支持哪些平台?

Image To Video 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Image To Video?

由 Ömer Karışman(@okaris)开发并维护,当前版本 v0.1.5。

💬 留言讨论