wavespeedai/wan-2.1-i2v-480p 🔢🖼️📝❓✓ → 🖼️

⭐ Official ▶️ 421.2K runs 📅 Feb 2025 ⚙️ Cog 0.16.1 🔗 GitHub ⚖️ License
image-to-video lora-compatible

About

Accelerated inference for Wan 2.1 14B image to video, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.

Example Output

Prompt:

"A woman is talking"

Output

Performance Metrics

39.24s Prediction Time
38.57s Total Time
All Input Parameters 
{
  "image": "https://replicate.delivery/pbxt/MZZyui7brAbh1d2AsyPtgPIByUwzSv6Uou8objC7zXEjLySc/1a8nt7yw5drm80cn05r89mjce0.png",
  "prompt": "A woman is talking",
  "max_area": "832x480",
  "fast_mode": "Balanced",
  "num_frames": 81,
  "sample_shift": 3,
  "sample_steps": 30,
  "frames_per_second": 16,
  "sample_guide_scale": 5
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation
image (required) Type: string
Image for use as the initial frame of the video.
prompt (required) Type: string
Text prompt for image generation
fast_mode Default: Balanced
Speed up generation with different levels of acceleration. Faster modes may degrade quality somewhat. The speedup is dependent on the content, so different videos may see different speedups.
lora_scale Type: numberDefault: 1Range: 0 - 4
Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. You may still need to experiment to find the best value for your particular lora.
aspect_ratio Default: 16:9
Aspect ratio of the output video.
lora_weights Type: string
Load LoRA weights. Supports HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet.
sample_shift Type: integerDefault: 3Range: 0 - 10
Flow shift parameter for video generation
sample_steps Type: integerDefault: 30Range: 1 - 40
Number of inference steps
negative_prompt Type: stringDefault:
Negative prompt to avoid certain elements
sample_guide_scale Type: numberDefault: 5Range: 1 - 10
Guidance scale for generation
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated videos
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Moderating content...
Image size: 8.2KB
Moderation complete in 0.97sec
Using seed: 1765621119
  0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
3%|▎         | 1/30 [00:01<00:44,  1.54s/it]
3%|▎         | 1/30 [00:01<00:44,  1.55s/it]
3%|▎         | 1/30 [00:01<00:44,  1.55s/it]
3%|▎         | 1/30 [00:01<00:44,  1.54s/it]
  3%|▎         | 1/30 [00:01<00:44,  1.55s/it]
3%|▎         | 1/30 [00:01<00:45,  1.55s/it]
  3%|▎         | 1/30 [00:01<00:45,  1.57s/it]
  3%|▎         | 1/30 [00:01<00:44,  1.55s/it]
7%|▋         | 2/30 [00:03<00:43,  1.55s/it]
7%|▋         | 2/30 [00:03<00:43,  1.55s/it]
7%|▋         | 2/30 [00:03<00:43,  1.55s/it]
7%|▋         | 2/30 [00:03<00:43,  1.56s/it]
7%|▋         | 2/30 [00:03<00:43,  1.57s/it]
  7%|▋         | 2/30 [00:03<00:43,  1.55s/it]
  7%|▋         | 2/30 [00:03<00:43,  1.56s/it]
  7%|▋         | 2/30 [00:03<00:43,  1.55s/it]
10%|█         | 3/30 [00:04<00:41,  1.55s/it]
10%|█         | 3/30 [00:04<00:41,  1.56s/it]
10%|█         | 3/30 [00:04<00:41,  1.55s/it]
10%|█         | 3/30 [00:04<00:42,  1.56s/it]
10%|█         | 3/30 [00:04<00:41,  1.55s/it]
10%|█         | 3/30 [00:04<00:42,  1.56s/it]
 10%|█         | 3/30 [00:04<00:42,  1.56s/it]
 10%|█         | 3/30 [00:04<00:41,  1.56s/it]
13%|█▎        | 4/30 [00:06<00:40,  1.56s/it]
13%|█▎        | 4/30 [00:06<00:40,  1.56s/it]
13%|█▎        | 4/30 [00:06<00:40,  1.56s/it]
13%|█▎        | 4/30 [00:06<00:40,  1.56s/it]
13%|█▎        | 4/30 [00:06<00:40,  1.56s/it]
13%|█▎        | 4/30 [00:06<00:40,  1.56s/it]
 13%|█▎        | 4/30 [00:06<00:40,  1.56s/it]
 13%|█▎        | 4/30 [00:06<00:40,  1.56s/it]
17%|█▋        | 5/30 [00:07<00:38,  1.56s/it]
17%|█▋        | 5/30 [00:07<00:38,  1.56s/it]
17%|█▋        | 5/30 [00:07<00:38,  1.56s/it]
17%|█▋        | 5/30 [00:07<00:38,  1.56s/it]
 17%|█▋        | 5/30 [00:07<00:38,  1.56s/it]
 17%|█▋        | 5/30 [00:07<00:39,  1.56s/it]
 17%|█▋        | 5/30 [00:07<00:38,  1.56s/it]
 17%|█▋        | 5/30 [00:07<00:38,  1.56s/it]
23%|██▎       | 7/30 [00:09<00:27,  1.17s/it]
23%|██▎       | 7/30 [00:09<00:27,  1.17s/it]
23%|██▎       | 7/30 [00:09<00:27,  1.17s/it]
 23%|██▎       | 7/30 [00:09<00:27,  1.17s/it]
23%|██▎       | 7/30 [00:09<00:27,  1.18s/it]
 23%|██▎       | 7/30 [00:09<00:27,  1.18s/it]
 23%|██▎       | 7/30 [00:09<00:27,  1.17s/it]
 23%|██▎       | 7/30 [00:09<00:27,  1.17s/it]
30%|███       | 9/30 [00:10<00:21,  1.02s/it]
30%|███       | 9/30 [00:10<00:21,  1.02s/it]
30%|███       | 9/30 [00:10<00:21,  1.02s/it]
 30%|███       | 9/30 [00:10<00:21,  1.02s/it]
 30%|███       | 9/30 [00:10<00:21,  1.02s/it]
30%|███       | 9/30 [00:11<00:21,  1.02s/it]
 30%|███       | 9/30 [00:11<00:21,  1.02s/it]
 30%|███       | 9/30 [00:10<00:21,  1.02s/it]
37%|███▋      | 11/30 [00:12<00:17,  1.07it/s]
37%|███▋      | 11/30 [00:12<00:17,  1.07it/s]
37%|███▋      | 11/30 [00:12<00:17,  1.07it/s]
37%|███▋      | 11/30 [00:12<00:17,  1.07it/s]
37%|███▋      | 11/30 [00:12<00:17,  1.07it/s]
37%|███▋      | 11/30 [00:12<00:17,  1.07it/s]
37%|███▋      | 11/30 [00:12<00:17,  1.07it/s]
 37%|███▋      | 11/30 [00:12<00:17,  1.07it/s]
43%|████▎     | 13/30 [00:14<00:15,  1.12it/s]
43%|████▎     | 13/30 [00:14<00:15,  1.12it/s]
43%|████▎     | 13/30 [00:14<00:15,  1.12it/s]
43%|████▎     | 13/30 [00:14<00:15,  1.12it/s]
 43%|████▎     | 13/30 [00:14<00:15,  1.12it/s]
43%|████▎     | 13/30 [00:14<00:15,  1.12it/s]
 43%|████▎     | 13/30 [00:14<00:15,  1.12it/s]
 43%|████▎     | 13/30 [00:14<00:15,  1.12it/s]
50%|█████     | 15/30 [00:15<00:12,  1.16it/s]
50%|█████     | 15/30 [00:15<00:12,  1.16it/s]
50%|█████     | 15/30 [00:15<00:12,  1.16it/s]
50%|█████     | 15/30 [00:15<00:12,  1.16it/s]
50%|█████     | 15/30 [00:15<00:12,  1.16it/s]
50%|█████     | 15/30 [00:15<00:12,  1.16it/s]
50%|█████     | 15/30 [00:15<00:12,  1.16it/s]
 50%|█████     | 15/30 [00:15<00:12,  1.16it/s]
57%|█████▋    | 17/30 [00:17<00:10,  1.19it/s]
57%|█████▋    | 17/30 [00:17<00:10,  1.19it/s]
57%|█████▋    | 17/30 [00:17<00:10,  1.19it/s]
57%|█████▋    | 17/30 [00:17<00:10,  1.19it/s]
57%|█████▋    | 17/30 [00:17<00:10,  1.19it/s]
57%|█████▋    | 17/30 [00:17<00:10,  1.19it/s]
 57%|█████▋    | 17/30 [00:17<00:10,  1.19it/s]
 57%|█████▋    | 17/30 [00:17<00:10,  1.19it/s]
63%|██████▎   | 19/30 [00:19<00:09,  1.20it/s]
63%|██████▎   | 19/30 [00:19<00:09,  1.20it/s]
63%|██████▎   | 19/30 [00:19<00:09,  1.20it/s]
63%|██████▎   | 19/30 [00:19<00:09,  1.20it/s]
63%|██████▎   | 19/30 [00:19<00:09,  1.20it/s]
63%|██████▎   | 19/30 [00:19<00:09,  1.20it/s]
 63%|██████▎   | 19/30 [00:19<00:09,  1.20it/s]
 63%|██████▎   | 19/30 [00:19<00:09,  1.20it/s]
70%|███████   | 21/30 [00:20<00:07,  1.22it/s]
70%|███████   | 21/30 [00:20<00:07,  1.22it/s]
70%|███████   | 21/30 [00:20<00:07,  1.22it/s]
70%|███████   | 21/30 [00:20<00:07,  1.22it/s]
70%|███████   | 21/30 [00:20<00:07,  1.22it/s]
70%|███████   | 21/30 [00:20<00:07,  1.22it/s]
 70%|███████   | 21/30 [00:20<00:07,  1.22it/s]
 70%|███████   | 21/30 [00:20<00:07,  1.22it/s]
77%|███████▋  | 23/30 [00:22<00:05,  1.22it/s]
77%|███████▋  | 23/30 [00:22<00:05,  1.22it/s]
77%|███████▋  | 23/30 [00:22<00:05,  1.22it/s]
77%|███████▋  | 23/30 [00:22<00:05,  1.22it/s]
77%|███████▋  | 23/30 [00:22<00:05,  1.22it/s]
77%|███████▋  | 23/30 [00:22<00:05,  1.22it/s]
 77%|███████▋  | 23/30 [00:22<00:05,  1.22it/s]
 77%|███████▋  | 23/30 [00:22<00:05,  1.22it/s]
80%|████████  | 24/30 [00:23<00:05,  1.05it/s]
80%|████████  | 24/30 [00:23<00:05,  1.05it/s]
80%|████████  | 24/30 [00:23<00:05,  1.05it/s]
80%|████████  | 24/30 [00:23<00:05,  1.05it/s]
80%|████████  | 24/30 [00:23<00:05,  1.05it/s]
80%|████████  | 24/30 [00:23<00:05,  1.05it/s]
 80%|████████  | 24/30 [00:23<00:05,  1.05it/s]
 80%|████████  | 24/30 [00:23<00:05,  1.05it/s]
83%|████████▎ | 25/30 [00:25<00:05,  1.08s/it]
83%|████████▎ | 25/30 [00:25<00:05,  1.08s/it]
83%|████████▎ | 25/30 [00:25<00:05,  1.08s/it]
83%|████████▎ | 25/30 [00:25<00:05,  1.08s/it]
83%|████████▎ | 25/30 [00:25<00:05,  1.08s/it]
83%|████████▎ | 25/30 [00:25<00:05,  1.08s/it]
83%|████████▎ | 25/30 [00:25<00:05,  1.08s/it]
 83%|████████▎ | 25/30 [00:25<00:05,  1.08s/it]
87%|████████▋ | 26/30 [00:26<00:04,  1.18s/it]
87%|████████▋ | 26/30 [00:26<00:04,  1.18s/it]
87%|████████▋ | 26/30 [00:26<00:04,  1.18s/it]
87%|████████▋ | 26/30 [00:26<00:04,  1.18s/it]
87%|████████▋ | 26/30 [00:26<00:04,  1.18s/it]
87%|████████▋ | 26/30 [00:26<00:04,  1.18s/it]
87%|████████▋ | 26/30 [00:26<00:04,  1.18s/it]
 87%|████████▋ | 26/30 [00:26<00:04,  1.18s/it]
90%|█████████ | 27/30 [00:28<00:03,  1.28s/it]
90%|█████████ | 27/30 [00:28<00:03,  1.28s/it]
90%|█████████ | 27/30 [00:28<00:03,  1.28s/it]
90%|█████████ | 27/30 [00:28<00:03,  1.28s/it]
90%|█████████ | 27/30 [00:28<00:03,  1.28s/it]
90%|█████████ | 27/30 [00:28<00:03,  1.28s/it]
 90%|█████████ | 27/30 [00:28<00:03,  1.28s/it]
 90%|█████████ | 27/30 [00:28<00:03,  1.28s/it]
93%|█████████▎| 28/30 [00:30<00:02,  1.35s/it]
93%|█████████▎| 28/30 [00:30<00:02,  1.35s/it]
93%|█████████▎| 28/30 [00:30<00:02,  1.35s/it]
93%|█████████▎| 28/30 [00:30<00:02,  1.35s/it]
93%|█████████▎| 28/30 [00:30<00:02,  1.35s/it]
93%|█████████▎| 28/30 [00:30<00:02,  1.35s/it]
 93%|█████████▎| 28/30 [00:30<00:02,  1.35s/it]
 93%|█████████▎| 28/30 [00:30<00:02,  1.35s/it]
97%|█████████▋| 29/30 [00:31<00:01,  1.41s/it]
97%|█████████▋| 29/30 [00:31<00:01,  1.41s/it]
97%|█████████▋| 29/30 [00:31<00:01,  1.41s/it]
97%|█████████▋| 29/30 [00:31<00:01,  1.41s/it]
97%|█████████▋| 29/30 [00:31<00:01,  1.41s/it]
97%|█████████▋| 29/30 [00:31<00:01,  1.41s/it]
97%|█████████▋| 29/30 [00:31<00:01,  1.41s/it]
 97%|█████████▋| 29/30 [00:31<00:01,  1.41s/it]
100%|██████████| 30/30 [00:33<00:00,  1.45s/it]
100%|██████████| 30/30 [00:33<00:00,  1.45s/it]
100%|██████████| 30/30 [00:33<00:00,  1.45s/it]
100%|██████████| 30/30 [00:33<00:00,  1.45s/it]
100%|██████████| 30/30 [00:33<00:00,  1.45s/it]
100%|██████████| 30/30 [00:33<00:00,  1.45s/it]
100%|██████████| 30/30 [00:33<00:00,  1.45s/it]
100%|██████████| 30/30 [00:33<00:00,  1.11s/it]
100%|██████████| 30/30 [00:33<00:00,  1.11s/it]
100%|██████████| 30/30 [00:33<00:00,  1.11s/it]
100%|██████████| 30/30 [00:33<00:00,  1.11s/it]
100%|██████████| 30/30 [00:33<00:00,  1.11s/it]
100%|██████████| 30/30 [00:33<00:00,  1.11s/it]
100%|██████████| 30/30 [00:33<00:00,  1.11s/it]
100%|██████████| 30/30 [00:33<00:00,  1.45s/it]
100%|██████████| 30/30 [00:33<00:00,  1.11s/it]
Time elapsed: 37.30s
Saving generated video to output.mp4
Version Details
Version ID
f6644fcfc305f4f9e29e789f01f62dfa43d1775c22db64705a05d6bf85957366
Version Created
August 4, 2025
Run on Replicate →