infsh login

# Generate dialogue audio
infsh app run falai/dia-tts --input '{
  "prompt": "[S1] Welcome to our product tour. Today I will show you three features that will save you hours every week."
}'

# Create talking head video with OmniHuman
infsh app run bytedance/omnihuman-1-5 --input '{
  "image": "path/to/portrait.png",
  "audio": "path/to/dialogue.mp3"
}'

# Generate a professional portrait background
infsh app run falai/flux-dev-lora --input '{
  "prompt": "professional headshot photograph of a friendly business person, soft studio lighting, clean grey background, head and shoulders, direct eye contact, neutral pleasant expression, high quality portrait photography"
}'

# Or remove background from existing portrait
infsh app run <bg-removal-app> --input '{
  "image": "path/to/portrait-with-background.png"
}'

# Simple narration
infsh app run falai/dia-tts --input '{
  "prompt": "[S1] Hi there! I am excited to share something with you today. We have been working on a feature that our users have been requesting for months... and it is finally here."
}'

# With emotion and pacing
infsh app run falai/dia-tts --input '{
  "prompt": "[S1] You know what is frustrating? Spending hours on tasks that should take minutes. (sighs) We have all been there. But what if I told you... there is a better way?"
}'

# 1. Generate or prepare audio
infsh app run falai/dia-tts --input '{
  "prompt": "[S1] Your narration script here."
}'

# 2. Generate talking head
infsh app run bytedance/omnihuman-1-5 --input '{
  "image": "portrait.png",
  "audio": "narration.mp3"
}'

# 1-2. Same as above

# 3. Add captions to the talking head video
infsh app run infsh/caption-videos --input '{
  "video": "talking-head.mp4",
  "caption_file": "captions.srt"
}'

# Generate audio segments
infsh app run falai/dia-tts --input '{"prompt": "[S1] Segment one script."}' --no-wait
infsh app run falai/dia-tts --input '{"prompt": "[S1] Segment two script."}' --no-wait
infsh app run falai/dia-tts --input '{"prompt": "[S1] Segment three script."}' --no-wait

# Generate talking head for each segment (same portrait for consistency)
infsh app run bytedance/omnihuman-1-5 --input '{"image": "portrait.png", "audio": "segment1.mp3"}' --no-wait
infsh app run bytedance/omnihuman-1-5 --input '{"image": "portrait.png", "audio": "segment2.mp3"}' --no-wait
infsh app run bytedance/omnihuman-1-5 --input '{"image": "portrait.png", "audio": "segment3.mp3"}' --no-wait

# Merge all segments
infsh app run infsh/media-merger --input '{
  "media": ["segment1.mp4", "segment2.mp4", "segment3.mp4"]
}'

# 1. Generate dialogue with two speakers
infsh app run falai/dia-tts --input '{
  "prompt": "[S1] So tell me about the new feature. [S2] Sure! We built a dashboard that shows real-time analytics. [S1] That sounds great. How long did it take? [S2] About two weeks from concept to launch."
}'

# 2. Create video with two characters
infsh app run bytedance/omnihuman-1-5 --input '{
  "image": "two-person-portrait.png",
  "audio": "dialogue.mp3"
}'

┌─────────────────────────────────┐
│          Headroom (minimal)     │
│  ┌───────────────────────────┐  │
│  │                           │  │
│  │     ● ─ ─ Eyes at 1/3 ─ ─│─ │ ← Eyes at top 1/3 line
│  │    /|\                    │  │
│  │     |   Head & shoulders  │  │
│  │    / \  visible           │  │
│  │                           │  │
│  └───────────────────────────┘  │
│       Crop below chest          │
└─────────────────────────────────┘

npx skills add inference-sh/skills@ai-avatar-video
npx skills add inference-sh/skills@ai-video-generation
npx skills add inference-sh/skills@text-to-speech