aicapcut/stable-video-diffusion-img2vid-xt-optimized 🔢🖼️✓ → 🖼️

▶️ 12.3K runs 📅 May 2024 ⚙️ Cog 0.9.6
image-to-video

About

Generate video

Example Output

Output

Performance Metrics

89.63s Prediction Time
461.38s Total Time
All Input Parameters
{
  "image": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/46d16cf2-c8d2-4825-a17d-3e6dd5ddcd56/original=true/02132-602138364-1girl,%20solo,%20barefoot,%20cloud,%20cloudy%20sky,%20dress,%20falling%20leaves,%20from%20behind,%20ghost,%20hill,%20outdoors,%20rain,%20sky,.jpeg",
  "width": 576,
  "height": 1024,
  "num_frames": 25,
  "cache_interval": 3,
  "cache_branch_id": 3,
  "enable_deepcache": true,
  "decode_chunk_size": 8,
  "num_inference_steps": 25
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
image (required) Type: string
Input image for img2vid mode
width Type: integerDefault: 1024
Width of output video
height Type: integerDefault: 576
Height of output video
num_frames Type: integerDefault: 25
Frame count
cache_interval Type: integerDefault: 3
Deepcache interval, set it larger to run faster at the expense of reduced image quality
cache_branch_id Type: integerDefault: 3
Deepcache branch id, set it smaller to run faster at the expense of reduced image quality (minimum: 0)
enable_deepcache Type: booleanDefault: true
Enable Deepcache can leads to faster inference speed
decode_chunk_size Type: integerDefault: 8
the VAE decodes frames in chunks instead of decoding them all together
num_inference_steps Type: integerDefault: 25
Steps
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 57843
  0%|          | 0/25 [00:00<?, ?it/s]
  4%|▍         | 1/25 [00:02<01:02,  2.60s/it]
  8%|▊         | 2/25 [00:04<00:44,  1.91s/it]
 12%|█▏        | 3/25 [00:05<00:37,  1.70s/it]
 16%|█▌        | 4/25 [00:08<00:42,  2.05s/it]
 20%|██        | 5/25 [00:09<00:36,  1.83s/it]
 24%|██▍       | 6/25 [00:10<00:32,  1.70s/it]
 28%|██▊       | 7/25 [00:13<00:35,  1.99s/it]
 32%|███▏      | 8/25 [00:14<00:30,  1.82s/it]
 36%|███▌      | 9/25 [00:16<00:27,  1.70s/it]
 40%|████      | 10/25 [00:18<00:29,  1.97s/it]
 44%|████▍     | 11/25 [00:20<00:25,  1.81s/it]
 48%|████▊     | 12/25 [00:21<00:22,  1.70s/it]
 52%|█████▏    | 13/25 [00:24<00:23,  1.96s/it]
 56%|█████▌    | 14/25 [00:25<00:19,  1.81s/it]
 60%|██████    | 15/25 [00:27<00:16,  1.69s/it]
 64%|██████▍   | 16/25 [00:29<00:17,  1.97s/it]
 68%|██████▊   | 17/25 [00:31<00:14,  1.81s/it]
 72%|███████▏  | 18/25 [00:32<00:11,  1.70s/it]
 76%|███████▌  | 19/25 [00:35<00:11,  1.97s/it]
 80%|████████  | 20/25 [00:36<00:09,  1.81s/it]
 84%|████████▍ | 21/25 [00:38<00:06,  1.70s/it]
 88%|████████▊ | 22/25 [00:40<00:05,  1.97s/it]
 92%|█████████▏| 23/25 [00:42<00:03,  1.82s/it]
 96%|█████████▌| 24/25 [00:43<00:01,  1.71s/it]
100%|██████████| 25/25 [00:46<00:00,  1.98s/it]
100%|██████████| 25/25 [00:46<00:00,  1.86s/it]
Version Details
Version ID
7b595c69ca428904c1907155b93a5580653d1e9dcd407612142595908650dd67
Version Created
May 4, 2024
Run on Replicate →