lucataco/longcat-video 🔢🖼️❓📝✓ → 🖼️

▶️ 90 runs 📅 Nov 2025 ⚙️ Cog 0.16.8

About

Example Output

Prompt:

"In a realistic photography style, a white boy around seven or eight years old sits on a park bench, wearing a light blue T-shirt, denim shorts, and white sneakers. He holds an ice cream cone with vanilla and chocolate flavors, and beside him is a medium-sized golden Labrador. Smiling, the boy offers the ice cream to the dog, who eagerly licks it with its tongue. The sun is shining brightly, and the background features a green lawn and several tall trees, creating a warm and loving scene."

Output

Performance Metrics

503.26s Prediction Time

823.16s Total Time

All Input Parameters

{
  "seed": 42,
  "width": 832,
  "height": 480,
  "prompt": "In a realistic photography style, a white boy around seven or eight years old sits on a park bench, wearing a light blue T-shirt, denim shorts, and white sneakers. He holds an ice cream cone with vanilla and chocolate flavors, and beside him is a medium-sized golden Labrador. Smiling, the boy offers the ice cream to the dog, who eagerly licks it with its tongue. The sun is shining brightly, and the background features a green lawn and several tall trees, creating a warm and loving scene.",
  "num_frames": 93,
  "resolution": "480p",
  "use_refine": false,
  "use_distill": true,
  "guidance_scale": 7,
  "negative_prompt": "ugly, blurry, low quality, static, subtitles, watermark, distorted, artifacts",
  "num_inference_steps": 25
}

Input Parameters

seed Type: integerDefault: 42: Random seed for reproducibility.
image Type: string: Optional image to drive image-to-video generation.
width Default: 832: Text-to-video frame width.
height Default: 480: Text-to-video frame height.
prompt (required) Type: string: Describe the video you want to generate.
num_frames Type: integerDefault: 93Range: 33 - 257: Number of frames to generate. Must satisfy pipeline requirements.
resolution Default: 480p: Image-to-video target resolution.
use_refine Type: booleanDefault: false: Run the optional refinement stage for higher quality output.
use_distill Type: booleanDefault: true: Use distilled weights for faster, lower-cost generation.
guidance_scale Type: numberDefault: 7Range: 0 - 20: Classifier-free guidance scale for the base stage.
negative_prompt Type: stringDefault: ugly, blurry, low quality, static, subtitles, watermark, distorted, artifacts: Negative prompt to avoid undesired content.
num_inference_steps Type: integerDefault: 25Range: 1 - 200: Number of diffusion steps for the base stage.

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Denoising:   0%|          | 0/16 [00:00<?, ?it/s]
Denoising:   6%|▋         | 1/16 [00:31<07:47, 31.15s/it]
Denoising:  12%|█▎        | 2/16 [01:02<07:15, 31.12s/it]
Denoising:  19%|█▉        | 3/16 [01:33<06:44, 31.12s/it]
Denoising:  25%|██▌       | 4/16 [02:04<06:13, 31.14s/it]
Denoising:  31%|███▏      | 5/16 [02:35<05:42, 31.14s/it]
Denoising:  38%|███▊      | 6/16 [03:06<05:11, 31.15s/it]
Denoising:  44%|████▍     | 7/16 [03:37<04:40, 31.15s/it]
Denoising:  50%|█████     | 8/16 [04:09<04:09, 31.15s/it]
Denoising:  56%|█████▋    | 9/16 [04:40<03:38, 31.15s/it]
Denoising:  62%|██████▎   | 10/16 [05:11<03:06, 31.16s/it]
Denoising:  69%|██████▉   | 11/16 [05:42<02:35, 31.16s/it]
Denoising:  75%|███████▌  | 12/16 [06:13<02:04, 31.16s/it]
Denoising:  81%|████████▏ | 13/16 [06:44<01:33, 31.15s/it]
Denoising:  88%|████████▊ | 14/16 [07:16<01:02, 31.15s/it]
Denoising:  94%|█████████▍| 15/16 [07:47<00:31, 31.14s/it]
Denoising: 100%|██████████| 16/16 [08:18<00:00, 31.14s/it]
Denoising: 100%|██████████| 16/16 [08:18<00:00, 31.15s/it]
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
- Avoid using `tokenizers` before the fork if possible
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
Multiple -pix_fmt options specified for stream 0, only the last option '-pix_fmt yuv420p' will be used.

Version Details

Version ID: a5e0db79259bd60fb7addd8d0f8976dbc880caeafa0214c07e4422d1ffe83873
Version Created: November 1, 2025

Run on Replicate →