vmodel/wan-2.1-i2v-480p
Experience accelerated image-to-video generation with wan-2.1-i2v-480p. Powered by the Wan 2.1 14B model suite, delivering efficient 480p video synthesis for research and production use.
Output: $0.5 / use or 2 uses / $1
Input
prompt * string
Prompt for video generation
image * image
Input image to start generating from
input image
num_frames int
Number of video frames. 81 frames give the best results
max_area enum
Maximum area of generated image. The input image will shrink to fit these dimensions
frames_per_second int
Frames per second. Note that the pricing of this model is based on the video duration at 16 fps
fast_mode enum
Speed up generation with different levels of acceleration. Faster modes may degrade quality somewhat. The speedup is dependent on the content, so different videos may see different speedups.
sample_steps int
Number of generation steps. Fewer steps means faster generation, at the expensive of output quality. 30 steps is sufficient for most prompts
sample_guide_scale int
Higher guide scale makes prompt adherence better, but can reduce variation
sample_shift int
Sample shift factor
lora_weights string
Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
lora_scale int
Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
seed int
Random seed. Leave blank to randomize the seed
disable_safety_checker boolean
Note: The website version of this model always runs with safety checks enabled. For details,see VModel's platform safety guidelines..
Disable safety checker for generated images
Reset
Output
{
  "task_id": "qaldrg3a9d9mfiw2tf",
  "user_id": 1,
  "version": "009719e7de9128f21878a3c96fe39663cc29c7d37103ca0b59f8a5d5b15ff73e",
  "error": null,
  "total_time": 30.8,
  "predict_time": 30.2,
  "logs": null,
  "output": [
    "https://vmodel.ai/data/model/vmodel/wan-2.1-i2v-480p/result.mp4"
  ],
  "status": "succeeded",
  "create_at": null,
  "input": {
    "prompt": "A woman is talking",
    "image": "https://vmodel.ai/data/model/vmodel/wan-2.1-i2v-480p/2.png",
    "max_area": "832x480",
    "fast_mode": "Balanced",
    "lora_scale": 1,
    "num_frames": 81,
    "sample_shift": 3,
    "sample_steps": 30,
    "frames_per_second": 16,
    "sample_guide_scale": 5,
    "disable_safety_checker": false
  }
}
Generated in: 30.2 seconds
Download
Examples
Pricing
Model pricing for vmodel/wan-2.1-i2v-480p. Looking for volume pricing? Get in touch.
When
⚙ using this model
$0.500
per use
or 2 uses for $1
Readme

Loading...