You're looking at a specific version of this model. Jump to the model overview.
dfischer /tokmeshmetal-4-epoch:b750029d
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
|
|
The text prompt describing your video scene.
|
| lora_url |
string
|
|
A URL pointing to your LoRA .safetensors file or a Hugging Face repo (e.g. 'user/repo' - uses the first .safetensors file).
|
| lora_strength |
number
|
1
Min: -10 Max: 10 |
Scale/strength for your LoRA.
|
| scheduler |
None
|
DPMSolverMultistepScheduler
|
Algorithm used to generate the video frames.
|
| steps |
integer
|
50
Min: 1 Max: 150 |
Number of diffusion steps.
|
| guidance_scale |
number
|
6
Max: 30 |
Overall influence of text vs. model.
|
| flow_shift |
integer
|
9
Max: 20 |
Video continuity factor (flow).
|
| num_frames |
integer
|
33
Min: 1 Max: 1440 |
How many frames (duration) in the resulting video.
|
| width |
integer
|
640
Min: 64 Max: 1536 |
Width for the generated video.
|
| height |
integer
|
360
Min: 64 Max: 1024 |
Height for the generated video.
|
| denoise_strength |
number
|
1
Max: 2 |
Controls how strongly noise is applied each step.
|
| force_offload |
boolean
|
True
|
Whether to force model layers offloaded to CPU.
|
| frame_rate |
integer
|
16
Min: 1 Max: 60 |
Video frame rate.
|
| crf |
integer
|
19
Max: 51 |
CRF (quality) for H264 encoding. Lower values = higher quality.
|
| enhance_weight |
number
|
0.3
Max: 2 |
Strength of the video enhancement effect.
|
| enhance_single |
boolean
|
True
|
Apply enhancement to individual frames.
|
| enhance_double |
boolean
|
True
|
Apply enhancement across frame pairs.
|
| enhance_start |
number
|
0
Max: 1 |
When to start enhancement in the video. Must be less than enhance_end.
|
| enhance_end |
number
|
1
Max: 1 |
When to end enhancement in the video. Must be greater than enhance_start.
|
| seed |
integer
|
Set a seed for reproducibility. Random by default.
|
|
| replicate_weights |
string
|
A .tar file containing LoRA weights from replicate.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}