WaveSpeedAI × WAN: SpeedUp 2nd - In CharacterJoin
WaveSpeed.ai
DashboardExploreInspiration
Home/Explore/3D Creation/wavespeed-ai/sam-3d-body
image-to-3d

image-to-3d

SAM 3D Body Generator

wavespeed-ai/sam-3d-body

Advanced SAM 3D body generation model for creating detailed 3D human body models from images with optional mask-based segmentation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Hint: You can drag and drop a file or click to upload

preview

Hint: You can drag and drop a file or click to upload

Idle

Your request will cost $0.02 per run.

For $1 you can run this model approximately 50 times.

ExamplesView all

README

SAM3 Video (Mask-Guided Video Editing)

wavespeed-ai/sam3-video is an advanced SAM-powered video editing model that applies prompt-based edits with optional mask guidance for cleaner, more controllable results. It’s built for production usage with a ready-to-use REST inference API, strong stability, no cold starts, and duration-based pricing.

🌟 Why it stands out

  • SAM-guided masking helps target edits more precisely (especially in cluttered scenes).
  • Prompt-driven editing for fast iteration (remove / clean / modify with natural language).
  • Optional apply_mask: you can enable mask application for tighter control, or disable it for general edits.
  • Production-ready inference: consistent performance and smoother frame-to-frame stability.

⚙️ Capabilities

  • Prompt-based video editing
  • Optional mask application via apply_mask (mask-guided control over where edits happen)
  • Designed to keep edits more consistent across frames (reduced flicker / drifting artifacts)
  • Works best for short-to-medium clips with clear subjects and stable motion

💰 Pricing

wavespeed-ai/sam3-video {"total_price": $max([5, $min([$number(get_duration_v2(video)), 600])]) / 5 * base_price} base price = 0.05

  • Duration is clamped to 5–600 seconds
  • Billed in 5-second units
  • Effective rate: $0.05 per 5s (≈ $0.01 per second)

Reference prices:

  • 5s → $0.05
  • 10s → $0.10
  • 30s → $0.30
  • 60s → $0.60
  • 120s → $1.20
  • 300s → $3.00
  • 600s → $6.00

How to use

  1. Upload the video (or provide a public URL).
  2. Write a prompt describing the edit (e.g., “remove the person in the background, keep lighting unchanged”).
  3. Toggle apply_mask if you want mask-guided editing.
  4. Run the model and download the edited result.

💡 Best Use Cases

  • Video object removal and background cleanup
  • Short-form content polishing (social clips, ads, product demos)
  • Mask-guided edits for busy scenes where precision matters
  • Fast creative iteration for editing concepts before heavy post-production

📝 Notes

  • Best results: stable footage, clear subject separation, minimal heavy motion blur.
  • apply_mask is recommended when you need tighter control over edited regions.
  • Very long videos are clamped at 600s for pricing and processing consistency.

More Video Models For you