ji4chenli/t2v-turbo-v2 ❓🔢📝 → 🖼️

▶️ 617 runs 📅 Oct 2024 ⚙️ Cog 0.9.23 🔗 GitHub 📄 Paper
text-to-video

About

Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance Design

Example Output

Prompt:

"With the style of low-poly game art, A majestic, white horse gallops gracefully across a moonlit beach"

Output

Performance Metrics

8.01s Prediction Time
121.12s Total Time
All Input Parameters 
{
  "fps": 8,
  "prompt": "With the style of low-poly game art, A majestic, white horse gallops gracefully across a moonlit beach",
  "motion_gs": 0.05,
  "num_frames": 16,
  "percentage": 0.5,
  "guidance_scale": 7.5,
  "num_inference_steps": 16
}
Input Parameters
fps Default: 8
FPS of the output video.
seed Type: integer
Random seed. Leave blank to randomize the seed
prompt Type: stringDefault: With the style of low-poly game art, A majestic, white horse gallops gracefully across a moonlit beach
Input prompt
motion_gs Type: numberDefault: 0.05
Set guidance for motion
num_frames Default: 16
Number of Video Frames
percentage Type: numberDefault: 0.5Range: 0 - 0.5
Percentage of steps to apply motion guidance (v2 w/ MG only)
guidance_scale Type: numberDefault: 7.5Range: 2 - 14
Scale for classifier-free guidance
num_inference_steps Type: integerDefault: 16Range: 4 - 50
Number of denoising steps
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Using seed: 23534
  0%|          | 0/16 [00:00<?, ?it/s]
  6%|▋         | 1/16 [00:00<00:06,  2.31it/s]
 12%|█▎        | 2/16 [00:00<00:03,  3.55it/s]
 19%|█▉        | 3/16 [00:00<00:03,  3.27it/s]
 25%|██▌       | 4/16 [00:01<00:03,  3.15it/s]
 31%|███▏      | 5/16 [00:01<00:03,  3.09it/s]
 38%|███▊      | 6/16 [00:01<00:03,  3.05it/s]
 44%|████▍     | 7/16 [00:02<00:02,  3.03it/s]
 50%|█████     | 8/16 [00:02<00:02,  3.02it/s]
 56%|█████▋    | 9/16 [00:02<00:02,  3.01it/s]
 62%|██████▎   | 10/16 [00:03<00:01,  3.01it/s]
 69%|██████▉   | 11/16 [00:03<00:01,  3.00it/s]
 75%|███████▌  | 12/16 [00:03<00:01,  3.00it/s]
 81%|████████▏ | 13/16 [00:04<00:01,  3.00it/s]
 88%|████████▊ | 14/16 [00:04<00:00,  3.00it/s]
 94%|█████████▍| 15/16 [00:04<00:00,  3.00it/s]
100%|██████████| 16/16 [00:05<00:00,  2.99it/s]
100%|██████████| 16/16 [00:05<00:00,  3.02it/s]
Version Details
Version ID
cdd7ad235a237a2076808758531221bae1a84422f30becd4fc881c9940093ce5
Version Created
October 14, 2024
Run on Replicate →