You're looking at a specific version of this model. Jump to the model overview.
phxdev1 /multi-lora-wan:9d2da68f
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| prompt |
string
|
Text prompt for video generation
|
|
| negative_prompt |
string
|
|
Things you do not want to see in your video
|
| image |
string
|
Image to use as a starting frame for image to video generation.
|
|
| aspect_ratio |
None
|
16:9
|
The aspect ratio of the video. 16:9, 9:16, 1:1, etc.
|
| frames |
None
|
81
|
The number of frames to generate (1 to 5 seconds)
|
| model |
None
|
14b
|
The model to use. 1.3b is faster, but 14b is better quality. A LORA either works with 1.3b or 14b, depending on the version it was trained on.
|
| resolution |
None
|
480p
|
The resolution of the video. 720p is not supported for 1.3b.
|
| lora_url |
string
|
Optional: The URL of a LORA to use (for single LoRA compatibility)
|
|
| lora_strength_model |
number
|
1
|
Strength of the LORA applied to the model. 0.0 is no LORA (for single LoRA compatibility).
|
| lora_strength_clip |
number
|
1
|
Strength of the LORA applied to the CLIP model. 0.0 is no LORA (for single LoRA compatibility).
|
| loras |
string
|
JSON string of LoRAs to apply. Format: "[{'url': 'lora1.safetensors', 'strength_model': 1.0, 'strength_clip': 1.0, 'enabled': true}]"
|
|
| enable_lora_memory_management |
boolean
|
False
|
Use progressive LoRA chaining (reduces VRAM) vs all-at-once chaining (faster but more VRAM)
|
| fast_mode |
None
|
Balanced
|
Speed up generation with different levels of acceleration. V2.1 mode uses LCM sampling for maximum speed.
|
| sample_steps |
integer
|
30
Min: 1 Max: 60 |
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 |
number
|
5
Max: 10 |
Higher guide scale makes prompt adherence better, but can reduce variation
|
| sample_shift |
number
|
8
Max: 10 |
Sample shift factor
|
| seed |
integer
|
Set a seed for reproducibility. Random by default.
|
|
| interpolation_multiplier |
integer
|
1
Min: 1 Max: 4 |
Frame interpolation multiplier for smoother video (V2.1 feature). 1 = no interpolation, 2 = double frames, etc.
|
| output_fps |
number
|
16
Min: 8 Max: 60 |
Target output FPS for interpolated video (V2.1 feature)
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}