cjwbw/controlvideo 📝❓🖼️🔢✓ → 🖼️
About
Training-free Controllable Text-to-Video Generation
Example Output
Prompt:
"James bond moonwalk on the beach, animation style."
Output
Performance Metrics
98.16s
Prediction Time
98.08s
Total Time
All Input Parameters
{
"prompt": "James bond moonwalk on the beach, animation style.",
"condition": "pose",
"video_path": "https://replicate.delivery/pbxt/Itp2gAJAkjTrIpLElNLmXjCtwLv5LnQTR2qWE15Qav0eyktR/moonwalk.mp4",
"video_length": 15,
"is_long_video": true,
"guidance_scale": 12.5,
"smoother_steps": "19, 20",
"num_inference_steps": 50
}
Input Parameters
- seed
- Random seed. Leave blank to randomize the seed
- prompt
- Text description of target video
- condition
- Condition of structure sequence
- video_path (required)
- source video
- video_length
- Length of synthesized video
- is_long_video
- Whether to use hierarchical sampler to produce long video
- guidance_scale
- Scale for classifier-free guidance
- smoother_steps
- Timesteps at which using interleaved-frame smoother, separate with comma
- num_inference_steps
- Number of denoising steps
Output Schema
Output
Example Execution Logs
Using seed: 8820 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<01:24, 1.73s/it] 4%|▍ | 2/50 [00:03<01:22, 1.72s/it] 6%|▌ | 3/50 [00:05<01:19, 1.70s/it] 8%|▊ | 4/50 [00:06<01:17, 1.68s/it] 10%|█ | 5/50 [00:08<01:16, 1.70s/it] 12%|█▏ | 6/50 [00:10<01:14, 1.70s/it] 14%|█▍ | 7/50 [00:11<01:12, 1.69s/it] 16%|█▌ | 8/50 [00:13<01:11, 1.69s/it] 18%|█▊ | 9/50 [00:15<01:08, 1.68s/it] 20%|██ | 10/50 [00:16<01:06, 1.67s/it] 22%|██▏ | 11/50 [00:18<01:05, 1.68s/it] 24%|██▍ | 12/50 [00:20<01:03, 1.67s/it] 26%|██▌ | 13/50 [00:21<01:02, 1.68s/it] 28%|██▊ | 14/50 [00:23<00:59, 1.64s/it] 30%|███ | 15/50 [00:25<00:57, 1.65s/it] 32%|███▏ | 16/50 [00:26<00:56, 1.67s/it] 34%|███▍ | 17/50 [00:28<00:54, 1.66s/it] 36%|███▌ | 18/50 [00:30<00:53, 1.67s/it] 38%|███▊ | 19/50 [00:31<00:52, 1.68s/it] 40%|████ | 20/50 [00:33<00:50, 1.68s/it] 42%|████▏ | 21/50 [00:35<00:48, 1.68s/it] 44%|████▍ | 22/50 [00:36<00:46, 1.67s/it] 46%|████▌ | 23/50 [00:38<00:44, 1.66s/it] 48%|████▊ | 24/50 [00:40<00:43, 1.65s/it] 50%|█████ | 25/50 [00:41<00:41, 1.66s/it] 52%|█████▏ | 26/50 [00:43<00:40, 1.68s/it] 54%|█████▍ | 27/50 [00:45<00:38, 1.66s/it] 56%|█████▌ | 28/50 [00:46<00:36, 1.66s/it] 58%|█████▊ | 29/50 [00:48<00:35, 1.68s/it] 60%|██████ | 30/50 [00:50<00:33, 1.67s/it] 62%|██████▏ | 31/50 [00:52<00:37, 1.98s/it] 64%|██████▍ | 32/50 [00:55<00:39, 2.20s/it] 66%|██████▌ | 33/50 [00:57<00:34, 2.03s/it] 68%|██████▊ | 34/50 [00:59<00:31, 1.94s/it] 70%|███████ | 35/50 [01:00<00:27, 1.85s/it] 72%|███████▏ | 36/50 [01:02<00:24, 1.77s/it] 74%|███████▍ | 37/50 [01:03<00:22, 1.74s/it] 76%|███████▌ | 38/50 [01:05<00:20, 1.70s/it] 78%|███████▊ | 39/50 [01:07<00:18, 1.67s/it] 80%|████████ | 40/50 [01:08<00:16, 1.68s/it] 82%|████████▏ | 41/50 [01:10<00:15, 1.69s/it] 84%|████████▍ | 42/50 [01:12<00:13, 1.70s/it] 86%|████████▌ | 43/50 [01:13<00:11, 1.69s/it] 88%|████████▊ | 44/50 [01:15<00:10, 1.69s/it] 90%|█████████ | 45/50 [01:17<00:08, 1.68s/it] 92%|█████████▏| 46/50 [01:18<00:06, 1.68s/it] 94%|█████████▍| 47/50 [01:20<00:05, 1.68s/it] 96%|█████████▌| 48/50 [01:22<00:03, 1.66s/it] 98%|█████████▊| 49/50 [01:23<00:01, 1.65s/it] 100%|██████████| 50/50 [01:25<00:00, 1.65s/it] 100%|██████████| 50/50 [01:25<00:00, 1.71s/it]
Version Details
- Version ID
91710b3f53c9c1cb958e7bf0ea982d21b666f6a3ff28c1670ee0c08355ced925- Version Created
- May 28, 2023