wan-video/wan-2.2-t2v-fast 🔢📝✓❓ → 🖼️
About
A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B text-to-video
Example Output
Prompt:
"A sports car is driving very fast along a beach at sunset"
Output
Performance Metrics
34.37s
Prediction Time
34.37s
Total Time
All Input Parameters
{
"prompt": "A sports car is driving very fast along a beach at sunset",
"go_fast": true,
"num_frames": 81,
"resolution": "480p",
"aspect_ratio": "16:9",
"sample_shift": 12,
"frames_per_second": 16
}
Input Parameters
- seed
- Random seed. Leave blank for random
- prompt (required)
- Prompt for video generation
- go_fast
- Go fast
- num_frames
- Number of video frames. 81 frames give the best results
- resolution
- Resolution of video. 16:9 corresponds to 832x480px, and 9:16 is 480x832px
- aspect_ratio
- Aspect ratio of video. 16:9 corresponds to 832x480px, and 9:16 is 480x832px
- sample_shift
- Sample shift factor
- optimize_prompt
- Translate prompt to Chinese before generation
- frames_per_second
- Frames per second. Note that the pricing of this model is based on the video duration at 16 fps
- interpolate_output
- Interpolate the generated video to 30 FPS using ffmpeg
- disable_safety_checker
- Disable safety checker for generated video.
- lora_scale_transformer
- Determines how strongly the transformer LoRA should be applied.
- lora_scale_transformer_2
- Determines how strongly the transformer_2 LoRA should be applied.
- lora_weights_transformer
- Load LoRA weights for transformer. Supports arbitrary .safetensors URLs from the Internet (for example, 'https://huggingface.co/Viktor1717/scandinavian-interior-style1/resolve/main/my_first_flux_lora_v1.safetensors')
- lora_weights_transformer_2
- Load LoRA weights for transformer_2. Supports arbitrary .safetensors URLs from the Internet. Can be different from transformer LoRA.
Output Schema
Output
Example Execution Logs
Inference took 33.80 seconds
Version Details
- Version ID
c483b1f7b892065bc58ebadb6381abf557f6b1f517d2ff0febb3fb635cf49b4d- Version Created
- January 16, 2026