Prediction

Model

zsxkib/wan-cakeify:995799f7

nyhhx4adgsrme0cnpjxtv75vkw

Status

Succeeded

Source

Web

Hardware

H100

Total duration

3m 47s

Created

9 months ago by zsxkib

Webhook

–

Input

prompt: A cute golden retriever puppy sits peacefully in CAKEIFY style, in grass surrounded by colorful flowers. A hand wearing a black glove enters the frame holding a sharp knife. The knife slowly cuts into the puppy, revealing that it's actually a hyper-realistic prop. The knife continues slicing, exposing layers of moist sponge cake and frosting inside. The cut piece tilts slightly, showing the detailed cake interior while maintaining the puppy's realistic exterior appearance. The final shot shows the partially sliced puppy cake sitting in the grass with flowers, with one perfect slice removed revealing its delicious interior
negative_prompt: Empty string
image: https://replicate.delivery/pbxt/Mh40Tagw3xWduL1PyW2FsBhvN1Dn1sbw1r47t7nnHGH0zImv/Screenshot%202025-03-19%20at%2011.24.14.png
aspect_ratio: 16:9
frames: 81
resolution: 480p
lora_strength_model: 1
lora_strength_clip: 1
fast_mode: Balanced
sample_steps: 30
sample_guide_scale: 5
sample_shift: 8

{
  "aspect_ratio": "16:9",
  "fast_mode": "Balanced",
  "frames": 81,
  "image": "https://replicate.delivery/pbxt/Mh40Tagw3xWduL1PyW2FsBhvN1Dn1sbw1r47t7nnHGH0zImv/Screenshot%202025-03-19%20at%2011.24.14.png",
  "lora_strength_clip": 1,
  "lora_strength_model": 1,
  "negative_prompt": "",
  "prompt": "A cute golden retriever puppy sits peacefully in CAKEIFY style, in grass surrounded by colorful flowers. A hand wearing a black glove enters the frame holding a sharp knife. The knife slowly cuts into the puppy, revealing that it's actually a hyper-realistic prop. The knife continues slicing, exposing layers of moist sponge cake and frosting inside. The cut piece tilts slightly, showing the detailed cake interior while maintaining the puppy's realistic exterior appearance. The final shot shows the partially sliced puppy cake sitting in the grass with flowers, with one perfect slice removed revealing its delicious interior",
  "resolution": "480p",
  "sample_guide_scale": 5,
  "sample_shift": 8,
  "sample_steps": 30
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_BZQ**********************************

This is your API token. Keep it to yourself.

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run zsxkib/wan-cakeify using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "zsxkib/wan-cakeify:995799f72c6f3ee1d96df4f7c6d0e5006d417aa025cbb5ad90d80ddffc68c0be",
  {
    input: {
      aspect_ratio: "16:9",
      fast_mode: "Balanced",
      frames: 81,
      image: "https://replicate.delivery/pbxt/Mh40Tagw3xWduL1PyW2FsBhvN1Dn1sbw1r47t7nnHGH0zImv/Screenshot%202025-03-19%20at%2011.24.14.png",
      lora_strength_clip: 1,
      lora_strength_model: 1,
      negative_prompt: "",
      prompt: "A cute golden retriever puppy sits peacefully in CAKEIFY style, in grass surrounded by colorful flowers. A hand wearing a black glove enters the frame holding a sharp knife. The knife slowly cuts into the puppy, revealing that it's actually a hyper-realistic prop. The knife continues slicing, exposing layers of moist sponge cake and frosting inside. The cut piece tilts slightly, showing the detailed cake interior while maintaining the puppy's realistic exterior appearance. The final shot shows the partially sliced puppy cake sitting in the grass with flowers, with one perfect slice removed revealing its delicious interior",
      resolution: "480p",
      sample_guide_scale: 5,
      sample_shift: 8,
      sample_steps: 30
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_BZQ**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run zsxkib/wan-cakeify using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "zsxkib/wan-cakeify:995799f72c6f3ee1d96df4f7c6d0e5006d417aa025cbb5ad90d80ddffc68c0be",
    input={
        "aspect_ratio": "16:9",
        "fast_mode": "Balanced",
        "frames": 81,
        "image": "https://replicate.delivery/pbxt/Mh40Tagw3xWduL1PyW2FsBhvN1Dn1sbw1r47t7nnHGH0zImv/Screenshot%202025-03-19%20at%2011.24.14.png",
        "lora_strength_clip": 1,
        "lora_strength_model": 1,
        "negative_prompt": "",
        "prompt": "A cute golden retriever puppy sits peacefully in CAKEIFY style, in grass surrounded by colorful flowers. A hand wearing a black glove enters the frame holding a sharp knife. The knife slowly cuts into the puppy, revealing that it's actually a hyper-realistic prop. The knife continues slicing, exposing layers of moist sponge cake and frosting inside. The cut piece tilts slightly, showing the detailed cake interior while maintaining the puppy's realistic exterior appearance. The final shot shows the partially sliced puppy cake sitting in the grass with flowers, with one perfect slice removed revealing its delicious interior",
        "resolution": "480p",
        "sample_guide_scale": 5,
        "sample_shift": 8,
        "sample_steps": 30
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_BZQ**********************************

This is your API token. Keep it to yourself.

Run zsxkib/wan-cakeify using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "zsxkib/wan-cakeify:995799f72c6f3ee1d96df4f7c6d0e5006d417aa025cbb5ad90d80ddffc68c0be",
    "input": {
      "aspect_ratio": "16:9",
      "fast_mode": "Balanced",
      "frames": 81,
      "image": "https://replicate.delivery/pbxt/Mh40Tagw3xWduL1PyW2FsBhvN1Dn1sbw1r47t7nnHGH0zImv/Screenshot%202025-03-19%20at%2011.24.14.png",
      "lora_strength_clip": 1,
      "lora_strength_model": 1,
      "negative_prompt": "",
      "prompt": "A cute golden retriever puppy sits peacefully in CAKEIFY style, in grass surrounded by colorful flowers. A hand wearing a black glove enters the frame holding a sharp knife. The knife slowly cuts into the puppy, revealing that it\'s actually a hyper-realistic prop. The knife continues slicing, exposing layers of moist sponge cake and frosting inside. The cut piece tilts slightly, showing the detailed cake interior while maintaining the puppy\'s realistic exterior appearance. The final shot shows the partially sliced puppy cake sitting in the grass with flowers, with one perfect slice removed revealing its delicious interior",
      "resolution": "480p",
      "sample_guide_scale": 5,
      "sample_shift": 8,
      "sample_steps": 30
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "id": "nyhhx4adgsrme0cnpjxtv75vkw",
  "model": "zsxkib/wan-cakeify",
  "version": "995799f72c6f3ee1d96df4f7c6d0e5006d417aa025cbb5ad90d80ddffc68c0be",
  "input": {
    "aspect_ratio": "16:9",
    "fast_mode": "Balanced",
    "frames": 81,
    "image": "https://replicate.delivery/pbxt/Mh40Tagw3xWduL1PyW2FsBhvN1Dn1sbw1r47t7nnHGH0zImv/Screenshot%202025-03-19%20at%2011.24.14.png",
    "lora_strength_clip": 1,
    "lora_strength_model": 1,
    "negative_prompt": "",
    "prompt": "A cute golden retriever puppy sits peacefully in CAKEIFY style, in grass surrounded by colorful flowers. A hand wearing a black glove enters the frame holding a sharp knife. The knife slowly cuts into the puppy, revealing that it's actually a hyper-realistic prop. The knife continues slicing, exposing layers of moist sponge cake and frosting inside. The cut piece tilts slightly, showing the detailed cake interior while maintaining the puppy's realistic exterior appearance. The final shot shows the partially sliced puppy cake sitting in the grass with flowers, with one perfect slice removed revealing its delicious interior",
    "resolution": "480p",
    "sample_guide_scale": 5,
    "sample_shift": 8,
    "sample_steps": 30
  },
  "logs": "Random seed set to: 3395008289\n2025-03-20T18:05:29Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp3ec62_04/weights url=https://replicate.delivery/xezq/HZMSOwxPxXYbCBGeQhCsMD6omrKQ9jfPxA8Xj4QUSPKC5e0oA/trained_model.tar\n2025-03-20T18:05:32Z | INFO  | [ Complete ] dest=/tmp/tmp3ec62_04/weights size=\"359 MB\" total_elapsed=2.855s url=https://replicate.delivery/xezq/HZMSOwxPxXYbCBGeQhCsMD6omrKQ9jfPxA8Xj4QUSPKC5e0oA/trained_model.tar\nChecking inputs\n✅ /tmp/inputs/image.png\n====================================\nChecking weights\n✅ wan_2.1_vae.safetensors exists in ComfyUI/models/vae\n✅ umt5_xxl_fp16.safetensors exists in ComfyUI/models/text_encoders\n⏳ Downloading wan2.1_i2v_480p_14B_bf16.safetensors to ComfyUI/models/diffusion_models\n✅ wan2.1_i2v_480p_14B_bf16.safetensors downloaded to ComfyUI/models/diffusion_models in 21.29s, size: 31270.88MB\n✅ 14b_6c163d784671748856bc8aef2c1122df.safetensors exists in loras directory\n✅ clip_vision_h.safetensors exists in ComfyUI/models/clip_vision\n====================================\nRunning workflow\n[ComfyUI] got prompt\nExecuting node 55, title: Load Image, class type: LoadImage\nExecuting node 56, title: Width and height for scaling image to ideal resolution 🪴, class type: Width and height for scaling image to ideal resolution 🪴\nExecuting node 57, title: 🔧 Image Resize, class type: ImageResize+\nExecuting node 60, title: Load CLIP Vision, class type: CLIPVisionLoader\n[ComfyUI] Requested to load CLIPVisionModelProjection\nExecuting node 59, title: CLIP Vision Encode, class type: CLIPVisionEncode\n[ComfyUI] loaded completely 129691.98263816834 1208.09814453125 True\nExecuting node 37, title: Load Diffusion Model, class type: UNETLoader\n[ComfyUI] model weight dtype torch.float16, manual cast: None\n[ComfyUI] model_type FLOW\nExecuting node 54, title: WanVideo Tea Cache (native), class type: WanVideoTeaCacheKJ\nExecuting node 49, title: Load LoRA, class type: LoraLoader\n[ComfyUI] Requested to load WanTEModel\nExecuting node 6, title: CLIP Text Encode (Positive Prompt), class type: CLIPTextEncode\n[ComfyUI] loaded completely 139319.35861854552 10835.4765625 True\nExecuting node 58, title: WanImageToVideo, class type: WanImageToVideo\nExecuting node 48, title: ModelSamplingSD3, class type: ModelSamplingSD3\nExecuting node 53, title: WanVideo Enhance A Video (native), class type: WanVideoEnhanceAVideoKJ\nExecuting node 3, title: KSampler, class type: KSampler\n[ComfyUI] Requested to load WAN21\n[ComfyUI] loaded completely 122348.68833397522 31269.802368164062 True\n[ComfyUI]\n[ComfyUI] 0%|          | 0/30 [00:00<?, ?it/s]\n[ComfyUI] 3%|▎         | 1/30 [00:08<03:59,  8.27s/it]\n[ComfyUI] 7%|▋         | 2/30 [00:18<04:26,  9.53s/it]\n[ComfyUI] 10%|█         | 3/30 [00:29<04:28,  9.94s/it]\n[ComfyUI] TeaCache: Initialized\n[ComfyUI]\n[ComfyUI] 13%|█▎        | 4/30 [00:41<04:48, 11.09s/it]\n[ComfyUI] 20%|██        | 6/30 [00:52<03:13,  8.08s/it]\n[ComfyUI] 23%|██▎       | 7/30 [01:03<03:22,  8.81s/it]\n[ComfyUI] 30%|███       | 9/30 [01:14<02:35,  7.38s/it]\n[ComfyUI] 33%|███▎      | 10/30 [01:14<01:52,  5.65s/it]\n[ComfyUI] 37%|███▋      | 11/30 [01:25<02:12,  6.95s/it]\n[ComfyUI] 43%|████▎     | 13/30 [01:36<01:47,  6.30s/it]\n[ComfyUI] 50%|█████     | 15/30 [01:47<01:29,  5.97s/it]\n[ComfyUI] 57%|█████▋    | 17/30 [01:58<01:15,  5.77s/it]\n[ComfyUI] 63%|██████▎   | 19/30 [02:08<01:02,  5.65s/it]\n[ComfyUI] 70%|███████   | 21/30 [02:19<00:50,  5.58s/it]\n[ComfyUI] 77%|███████▋  | 23/30 [02:19<00:26,  3.84s/it]\n[ComfyUI] 80%|████████  | 24/30 [02:30<00:30,  5.11s/it]\n[ComfyUI] 87%|████████▋ | 26/30 [02:30<00:13,  3.38s/it]\n[ComfyUI] 93%|█████████▎| 28/30 [02:41<00:08,  4.05s/it]\n[ComfyUI] 97%|█████████▋| 29/30 [02:52<00:05,  5.32s/it]\n[ComfyUI] 100%|██████████| 30/30 [03:03<00:00,  6.48s/it]\nExecuting node 8, title: VAE Decode, class type: VAEDecode\nExecuting node 50, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] 100%|██████████| 30/30 [03:03<00:00,  6.10s/it]\n[ComfyUI] Prompt executed in 201.50 seconds\noutputs:  {'50': {'gifs': [{'filename': 'R8_Wan_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 16.0, 'workflow': 'R8_Wan_00001.png', 'fullpath': '/tmp/outputs/R8_Wan_00001.mp4'}]}}\n====================================\nR8_Wan_00001.png\nR8_Wan_00001.mp4",
  "output": [
    "https://replicate.delivery/xezq/Tf07salRJi3CKCErUxTcye86ufL60HySzXobCrysVUNWeCqRB/R8_Wan_00001.mp4"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2025-03-20T18:05:28.838Z",
  "started_at": "2025-03-20T18:05:29.576464Z",
  "completed_at": "2025-03-20T18:09:15.566938Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/nyhhx4adgsrme0cnpjxtv75vkw/cancel",
    "get": "https://api.replicate.com/v1/predictions/nyhhx4adgsrme0cnpjxtv75vkw",
    "stream": "https://stream.replicate.com/v1/files/bcwr-oa7ydvnaqaces2l34fl67r2s363tzvxzk3bseig76arp3m3xisyq",
    "web": "https://replicate.com/p/nyhhx4adgsrme0cnpjxtv75vkw"
  },
  "metrics": {
    "predict_time": 225.990473384,
    "total_time": 226.728938
  }
}

Generated in

3 minutes 46 seconds

Tweak it Report

Random seed set to: 3395008289 2025-03-20T18:05:29Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp3ec62_04/weights url=https://replicate.delivery/xezq/HZMSOwxPxXYbCBGeQhCsMD6omrKQ9jfPxA8Xj4QUSPKC5e0oA/trained_model.tar 2025-03-20T18:05:32Z | INFO | [ Complete ] dest=/tmp/tmp3ec62_04/weights size="359 MB" total_elapsed=2.855s url=https://replicate.delivery/xezq/HZMSOwxPxXYbCBGeQhCsMD6omrKQ9jfPxA8Xj4QUSPKC5e0oA/trained_model.tar Checking inputs ✅ /tmp/inputs/image.png ==================================== Checking weights ✅ wan_2.1_vae.safetensors exists in ComfyUI/models/vae ✅ umt5_xxl_fp16.safetensors exists in ComfyUI/models/text_encoders ⏳ Downloading wan2.1_i2v_480p_14B_bf16.safetensors to ComfyUI/models/diffusion_models ✅ wan2.1_i2v_480p_14B_bf16.safetensors downloaded to ComfyUI/models/diffusion_models in 21.29s, size: 31270.88MB ✅ 14b_6c163d784671748856bc8aef2c1122df.safetensors exists in loras directory ✅ clip_vision_h.safetensors exists in ComfyUI/models/clip_vision ==================================== Running workflow [ComfyUI] got prompt Executing node 55, title: Load Image, class type: LoadImage Executing node 56, title: Width and height for scaling image to ideal resolution 🪴, class type: Width and height for scaling image to ideal resolution 🪴 Executing node 57, title: 🔧 Image Resize, class type: ImageResize+ Executing node 60, title: Load CLIP Vision, class type: CLIPVisionLoader [ComfyUI] Requested to load CLIPVisionModelProjection Executing node 59, title: CLIP Vision Encode, class type: CLIPVisionEncode [ComfyUI] loaded completely 129691.98263816834 1208.09814453125 True Executing node 37, title: Load Diffusion Model, class type: UNETLoader [ComfyUI] model weight dtype torch.float16, manual cast: None [ComfyUI] model_type FLOW Executing node 54, title: WanVideo Tea Cache (native), class type: WanVideoTeaCacheKJ Executing node 49, title: Load LoRA, class type: LoraLoader [ComfyUI] Requested to load WanTEModel Executing node 6, title: CLIP Text Encode (Positive Prompt), class type: CLIPTextEncode [ComfyUI] loaded completely 139319.35861854552 10835.4765625 True Executing node 58, title: WanImageToVideo, class type: WanImageToVideo Executing node 48, title: ModelSamplingSD3, class type: ModelSamplingSD3 Executing node 53, title: WanVideo Enhance A Video (native), class type: WanVideoEnhanceAVideoKJ Executing node 3, title: KSampler, class type: KSampler [ComfyUI] Requested to load WAN21 [ComfyUI] loaded completely 122348.68833397522 31269.802368164062 True [ComfyUI] [ComfyUI] 0%| | 0/30 [00:00<?, ?it/s] [ComfyUI] 3%|▎ | 1/30 [00:08<03:59, 8.27s/it] [ComfyUI] 7%|▋ | 2/30 [00:18<04:26, 9.53s/it] [ComfyUI] 10%|█ | 3/30 [00:29<04:28, 9.94s/it] [ComfyUI] TeaCache: Initialized [ComfyUI] [ComfyUI] 13%|█▎ | 4/30 [00:41<04:48, 11.09s/it] [ComfyUI] 20%|██ | 6/30 [00:52<03:13, 8.08s/it] [ComfyUI] 23%|██▎ | 7/30 [01:03<03:22, 8.81s/it] [ComfyUI] 30%|███ | 9/30 [01:14<02:35, 7.38s/it] [ComfyUI] 33%|███▎ | 10/30 [01:14<01:52, 5.65s/it] [ComfyUI] 37%|███▋ | 11/30 [01:25<02:12, 6.95s/it] [ComfyUI] 43%|████▎ | 13/30 [01:36<01:47, 6.30s/it] [ComfyUI] 50%|█████ | 15/30 [01:47<01:29, 5.97s/it] [ComfyUI] 57%|█████▋ | 17/30 [01:58<01:15, 5.77s/it] [ComfyUI] 63%|██████▎ | 19/30 [02:08<01:02, 5.65s/it] [ComfyUI] 70%|███████ | 21/30 [02:19<00:50, 5.58s/it] [ComfyUI] 77%|███████▋ | 23/30 [02:19<00:26, 3.84s/it] [ComfyUI] 80%|████████ | 24/30 [02:30<00:30, 5.11s/it] [ComfyUI] 87%|████████▋ | 26/30 [02:30<00:13, 3.38s/it] [ComfyUI] 93%|█████████▎| 28/30 [02:41<00:08, 4.05s/it] [ComfyUI] 97%|█████████▋| 29/30 [02:52<00:05, 5.32s/it] [ComfyUI] 100%|██████████| 30/30 [03:03<00:00, 6.48s/it] Executing node 8, title: VAE Decode, class type: VAEDecode Executing node 50, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine [ComfyUI] 100%|██████████| 30/30 [03:03<00:00, 6.10s/it] [ComfyUI] Prompt executed in 201.50 seconds outputs: {'50': {'gifs': [{'filename': 'R8_Wan_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 16.0, 'workflow': 'R8_Wan_00001.png', 'fullpath': '/tmp/outputs/R8_Wan_00001.mp4'}]}} ==================================== R8_Wan_00001.png R8_Wan_00001.mp4