lucataco/ltx-video-iclora 🔢📝❓🖼️ → 🖼️

▶️ 96 runs 📅 Jul 2025 ⚙️ Cog 0.15.11 🔗 GitHub

About

LTX Video 0.9.7 Distilled with ICLoRAs

Example Output

Prompt:

"Two elderly men with large white beards engage in a fight in a lush park setting, they lunge at each other with their golf clubs with determined focus amid the green canopy of trees"

Output

Performance Metrics

32.36s Prediction Time

32.36s Total Time

All Input Parameters

{
  "fps": 24,
  "seed": 0,
  "prompt": "Two elderly men with large white beards engage in a fight in a lush park setting, they lunge at each other with their golf clubs with determined focus amid the green canopy of trees",
  "num_frames": 121,
  "aspect_ratio": "match_input_video",
  "control_type": "canny",
  "guidance_scale": 1,
  "negative_prompt": "worst quality, inconsistent motion, blurry, jittery, distorted",
  "reference_video": "https://replicate.delivery/pbxt/NMc35bj7yOUe9dClRGg150T3BT5sIZTJ6S3XO49PvcjcsJgx/replicate-prediction-kzhcsj5c31rm80cr1y3s4cwbmm.mp4",
  "num_inference_steps": 7
}

Input Parameters

fps Type: integerDefault: 24Range: 1 - 60: Frames per second for the generated video
seed Type: integerDefault: 0: Random seed for reproducibility (0 for random)
prompt Type: stringDefault: A beautiful landscape with flowing water: Text prompt describing the desired video
num_frames Type: integerDefault: 121Range: 9 - 257: Number of frames in the generated video
aspect_ratio Default: match_input_video: Aspect ratio for the generated video
control_type Default: canny: Type of control guidance
guidance_scale Type: numberDefault: 1Range: 1 - 5: Guidance scale for generation
negative_prompt Type: stringDefault: worst quality, inconsistent motion, blurry, jittery, distorted: Negative prompt describing what to avoid
reference_video (required) Type: string: Reference video for control guidance
num_inference_steps Type: integerDefault: 7Range: 5 - 10: Number of inference steps

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Using seed: 28668
Using closest standard aspect ratio: 16:9
Calculated dimensions: 1248x704 (aspect ratio: 1.773)
canny LoRA already loaded
Processing video for canny control...
  0%|          | 0/7 [00:00<?, ?it/s]
 14%|█▍        | 1/7 [00:01<00:07,  1.18s/it]
 29%|██▊       | 2/7 [00:02<00:05,  1.07s/it]
 43%|████▎     | 3/7 [00:03<00:04,  1.12s/it]
 57%|█████▋    | 4/7 [00:04<00:03,  1.14s/it]
 71%|███████▏  | 5/7 [00:05<00:02,  1.16s/it]
 86%|████████▌ | 6/7 [00:06<00:01,  1.16s/it]
100%|██████████| 7/7 [00:08<00:00,  1.17s/it]
100%|██████████| 7/7 [00:08<00:00,  1.15s/it]
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:02<00:08,  2.88s/it]
 50%|█████     | 2/4 [00:05<00:05,  2.63s/it]
 75%|███████▌  | 3/4 [00:08<00:02,  2.75s/it]
100%|██████████| 4/4 [00:11<00:00,  2.80s/it]
100%|██████████| 4/4 [00:11<00:00,  2.78s/it]

Version Details

Version ID: 4cb7ff7f0a3cf4cb577ebc641c82b3160f6821f5f312133472933cf267c7880c
Version Created: July 17, 2025

Run on Replicate →