✨ Fast 4 steps Wan 2.1 I2V (14B) with CausVid LoRA
🖼️ Input Image (auto-resized to target H/W)
Drop Image Here
- or -
Click to Upload
✏️ Prompt
make this image come alive, cinematic motion, smooth animation
⏱️ Duration (seconds)
Clamped to model's 8-120 frames at 24fps.
↺
0.3
5
⚙️ Advanced Settings
▼
❌ Negative Prompt
Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards, watermark, text, signature
🎲 Seed
↺
0
2147483647
🔀 Randomize seed
📏 Output Height (multiple of 32)
↺
128
896
📐 Output Width (multiple of 32)
↺
128
896
🚀 Inference Steps
↺
1
30
🎯 Guidance Scale
↺
0
20
🧩 Optional LoRA
⚡ LoRA Strength
↺
0
1
🎬 Generate Video
🎥 Generated Video
