fofr / wan-14b-my-subconscious

  • Public
  • 49 runs
  • H100
Iterate in playground

Run fofr/wan-14b-my-subconscious with an API

Input schema

seedinteger

Set a seed for reproducibility. Random by default.

imageuri

Image to use as a starting frame for image to video generation.

framesinteger

The number of frames to generate (1 to 5 seconds)

Default
81
promptstring

Text prompt for video generation

fast_modestring

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.

Default
"Balanced"
resolutionstring

The resolution of the video. 720p is not supported for 1.3b.

Default
"480p"
aspect_ratiostring

The aspect ratio of the video. 16:9, 9:16, 1:1, etc.

Default
"16:9"
sample_shiftnumber

Sample shift factor

Default
8
Maximum
10
sample_stepsinteger

Number of generation steps. Fewer steps means faster generation, at the expensive of output quality. 30 steps is sufficient for most prompts

Default
30
Minimum
1
Maximum
60
negative_promptstring

Things you do not want to see in your video

lora_strength_clipnumber

Strength of the LORA applied to the CLIP model. 0.0 is no LORA.

Default
1
sample_guide_scalenumber

Higher guide scale makes prompt adherence better, but can reduce variation

Default
5
Maximum
10
lora_strength_modelnumber

Strength of the LORA applied to the model. 0.0 is no LORA.

Default
1

Output schema

Type
uri[]