shridharathi/ghibli-vid – Run with an API on Replicate

shridharathi / ghibli-vid

Make a video of anything in Studio Ghibli style

Cold

Public
91 runs
H100

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

GHIBLI style, anime, a girl running through new york cityGHIBLI style, anime, a girl running through new york city

Text prompt for video generation

negative_prompt

string

Shift + Return to add a new line

Things you do not want to see in your video

Default: ""

image

file

Image to use as a starting frame for image to video generation.

aspect_ratio

string

The aspect ratio of the video. 16:9, 9:16, 1:1, etc.

Default: "16:9"

frames

integer

The number of frames to generate (1 to 5 seconds)

Default: 81

resolution

string

The resolution of the video. 720p is not supported for 1.3b.

Default: "480p"

lora_strength_model

number

Strength of the LORA applied to the model. 0.0 is no LORA.

Default: 1

lora_strength_clip

number

Strength of the LORA applied to the CLIP model. 0.0 is no LORA.

Default: 1

fast_mode

string

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.

Default: "Balanced"

sample_steps

integer

(minimum: 1, maximum: 60)

Number of generation steps. Fewer steps means faster generation, at the expensive of output quality. 30 steps is sufficient for most prompts

Default: 30

sample_guide_scale

number

(minimum: 0, maximum: 10)

Higher guide scale makes prompt adherence better, but can reduce variation

Default: 5

sample_shift

number

(minimum: 0, maximum: 10)

Sample shift factor

Default: 8

seed

integer

Set a seed for reproducibility. Random by default.

Run this model in Node.js with one line of code:

npx create-replicate --model=shridharathi/ghibli-vid

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

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

Run shridharathi/ghibli-vid using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "shridharathi/ghibli-vid:e65c22b73e9df842276a6321a718152d591ddad2e36eb6441606bc06c3d133d0",
  {
    input: {
      frames: 81,
      prompt: "GHIBLI style, anime, a girl running through new york city",
      fast_mode: "Balanced",
      resolution: "480p",
      aspect_ratio: "16:9",
      sample_shift: 8,
      sample_steps: 30,
      negative_prompt: "",
      lora_strength_clip: 1,
      sample_guide_scale: 5,
      lora_strength_model: 1
    }
  }
);

// 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=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run shridharathi/ghibli-vid using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "shridharathi/ghibli-vid:e65c22b73e9df842276a6321a718152d591ddad2e36eb6441606bc06c3d133d0",
    input={
        "frames": 81,
        "prompt": "GHIBLI style, anime, a girl running through new york city",
        "fast_mode": "Balanced",
        "resolution": "480p",
        "aspect_ratio": "16:9",
        "sample_shift": 8,
        "sample_steps": 30,
        "negative_prompt": "",
        "lora_strength_clip": 1,
        "sample_guide_scale": 5,
        "lora_strength_model": 1
    }
)
print(output)

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=<paste-your-token-here>

Find your API token in your account settings.

Run shridharathi/ghibli-vid 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": "shridharathi/ghibli-vid:e65c22b73e9df842276a6321a718152d591ddad2e36eb6441606bc06c3d133d0",
    "input": {
      "frames": 81,
      "prompt": "GHIBLI style, anime, a girl running through new york city",
      "fast_mode": "Balanced",
      "resolution": "480p",
      "aspect_ratio": "16:9",
      "sample_shift": 8,
      "sample_steps": 30,
      "negative_prompt": "",
      "lora_strength_clip": 1,
      "sample_guide_scale": 5,
      "lora_strength_model": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/shridharathi/ghibli-vid@sha256:e65c22b73e9df842276a6321a718152d591ddad2e36eb6441606bc06c3d133d0 \
  -i 'frames=81' \
  -i 'prompt="GHIBLI style, anime, a girl running through new york city"' \
  -i 'fast_mode="Balanced"' \
  -i 'resolution="480p"' \
  -i 'aspect_ratio="16:9"' \
  -i 'sample_shift=8' \
  -i 'sample_steps=30' \
  -i 'negative_prompt=""' \
  -i 'lora_strength_clip=1' \
  -i 'sample_guide_scale=5' \
  -i 'lora_strength_model=1'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/shridharathi/ghibli-vid@sha256:e65c22b73e9df842276a6321a718152d591ddad2e36eb6441606bc06c3d133d0
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "frames": 81,
      "prompt": "GHIBLI style, anime, a girl running through new york city",
      "fast_mode": "Balanced",
      "resolution": "480p",
      "aspect_ratio": "16:9",
      "sample_shift": 8,
      "sample_steps": 30,
      "negative_prompt": "",
      "lora_strength_clip": 1,
      "sample_guide_scale": 5,
      "lora_strength_model": 1
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2025-03-27T20:34:22.942783Z",
  "created_at": "2025-03-27T20:31:34.319000Z",
  "data_removed": false,
  "error": null,
  "id": "n5s2qschnxrma0cnv56s32pqbm",
  "input": {
    "frames": 81,
    "prompt": "GHIBLI style, anime, a girl running through new york city",
    "fast_mode": "Balanced",
    "resolution": "480p",
    "aspect_ratio": "16:9",
    "sample_shift": 8,
    "sample_steps": 30,
    "negative_prompt": "",
    "lora_strength_clip": 1,
    "sample_guide_scale": 5,
    "lora_strength_model": 1
  },
  "logs": "Random seed set to: 874149996\n✅ 14b_d21761924b1fb223ad93c834ec74afd9.safetensors already cached\nChecking inputs\n====================================\nChecking weights\n✅ 14b_d21761924b1fb223ad93c834ec74afd9.safetensors exists in loras directory\n✅ umt5_xxl_fp16.safetensors exists in ComfyUI/models/text_encoders\n✅ wan2.1_t2v_14B_bf16.safetensors exists in ComfyUI/models/diffusion_models\n✅ wan_2.1_vae.safetensors exists in ComfyUI/models/vae\n====================================\nRunning workflow\n[ComfyUI] got prompt\nExecuting node 6, title: CLIP Text Encode (Positive Prompt), class type: CLIPTextEncode\nExecuting node 3, title: KSampler, class type: KSampler\n[ComfyUI]\n[ComfyUI] 0%|          | 0/30 [00:00<?, ?it/s]\n[ComfyUI] Resetting TeaCache state\n[ComfyUI]\n[ComfyUI] 3%|▎         | 1/30 [00:06<03:12,  6.62s/it]\n[ComfyUI] 7%|▋         | 2/30 [00:16<03:51,  8.28s/it]\n[ComfyUI] 10%|█         | 3/30 [00:25<03:57,  8.80s/it]\n[ComfyUI] TeaCache: Initialized\n[ComfyUI]\n[ComfyUI] 13%|█▎        | 4/30 [00:37<04:26, 10.26s/it]\n[ComfyUI] 20%|██        | 6/30 [00:47<02:58,  7.42s/it]\n[ComfyUI] 27%|██▋       | 8/30 [00:57<02:19,  6.34s/it]\n[ComfyUI] 33%|███▎      | 10/30 [01:07<01:55,  5.80s/it]\n[ComfyUI] 40%|████      | 12/30 [01:17<01:38,  5.48s/it]\n[ComfyUI] 47%|████▋     | 14/30 [01:27<01:24,  5.29s/it]\n[ComfyUI] 53%|█████▎    | 16/30 [01:36<01:12,  5.17s/it]\n[ComfyUI] 60%|██████    | 18/30 [01:46<01:00,  5.08s/it]\n[ComfyUI] 67%|██████▋   | 20/30 [01:56<00:50,  5.03s/it]\n[ComfyUI] 73%|███████▎  | 22/30 [02:06<00:39,  4.99s/it]\n[ComfyUI] 80%|████████  | 24/30 [02:16<00:29,  4.97s/it]\n[ComfyUI] 87%|████████▋ | 26/30 [02:25<00:19,  4.95s/it]\n[ComfyUI] 93%|█████████▎| 28/30 [02:35<00:09,  4.94s/it]\n[ComfyUI] 100%|██████████| 30/30 [02:45<00:00,  4.93s/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 [02:45<00:00,  5.52s/it]\n[ComfyUI] Prompt executed in 168.43 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",
  "metrics": {
    "predict_time": 168.615737712,
    "total_time": 168.623783
  },
  "output": [
    "https://replicate.delivery/xezq/4T0Ff7e3Yvjy30HeYRQjqWMG19epscJK6DEdFQ5LYTW5EazRB/R8_Wan_00001.mp4"
  ],
  "started_at": "2025-03-27T20:31:34.327045Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-o2s47uywl3fvj5h7ewud4q4ckzdsabnncpthh33qdonbw6cxo75q",
    "get": "https://api.replicate.com/v1/predictions/n5s2qschnxrma0cnv56s32pqbm",
    "cancel": "https://api.replicate.com/v1/predictions/n5s2qschnxrma0cnv56s32pqbm/cancel"
  },
  "version": "e65c22b73e9df842276a6321a718152d591ddad2e36eb6441606bc06c3d133d0"
}

Generated in

2 minutes 49 seconds

Tweak it ShareReport

Random seed set to: 874149996
✅ 14b_d21761924b1fb223ad93c834ec74afd9.safetensors already cached
Checking inputs
====================================
Checking weights
✅ 14b_d21761924b1fb223ad93c834ec74afd9.safetensors exists in loras directory
✅ umt5_xxl_fp16.safetensors exists in ComfyUI/models/text_encoders
✅ wan2.1_t2v_14B_bf16.safetensors exists in ComfyUI/models/diffusion_models
✅ wan_2.1_vae.safetensors exists in ComfyUI/models/vae
====================================
Running workflow
[ComfyUI] got prompt
Executing node 6, title: CLIP Text Encode (Positive Prompt), class type: CLIPTextEncode
Executing node 3, title: KSampler, class type: KSampler
[ComfyUI]
[ComfyUI] 0%|          | 0/30 [00:00<?, ?it/s]
[ComfyUI] Resetting TeaCache state
[ComfyUI]
[ComfyUI] 3%|▎         | 1/30 [00:06<03:12,  6.62s/it]
[ComfyUI] 7%|▋         | 2/30 [00:16<03:51,  8.28s/it]
[ComfyUI] 10%|█         | 3/30 [00:25<03:57,  8.80s/it]
[ComfyUI] TeaCache: Initialized
[ComfyUI]
[ComfyUI] 13%|█▎        | 4/30 [00:37<04:26, 10.26s/it]
[ComfyUI] 20%|██        | 6/30 [00:47<02:58,  7.42s/it]
[ComfyUI] 27%|██▋       | 8/30 [00:57<02:19,  6.34s/it]
[ComfyUI] 33%|███▎      | 10/30 [01:07<01:55,  5.80s/it]
[ComfyUI] 40%|████      | 12/30 [01:17<01:38,  5.48s/it]
[ComfyUI] 47%|████▋     | 14/30 [01:27<01:24,  5.29s/it]
[ComfyUI] 53%|█████▎    | 16/30 [01:36<01:12,  5.17s/it]
[ComfyUI] 60%|██████    | 18/30 [01:46<01:00,  5.08s/it]
[ComfyUI] 67%|██████▋   | 20/30 [01:56<00:50,  5.03s/it]
[ComfyUI] 73%|███████▎  | 22/30 [02:06<00:39,  4.99s/it]
[ComfyUI] 80%|████████  | 24/30 [02:16<00:29,  4.97s/it]
[ComfyUI] 87%|████████▋ | 26/30 [02:25<00:19,  4.95s/it]
[ComfyUI] 93%|█████████▎| 28/30 [02:35<00:09,  4.94s/it]
[ComfyUI] 100%|██████████| 30/30 [02:45<00:00,  4.93s/it]
Executing node 8, title: VAE Decode, class type: VAEDecode
Executing node 50, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine
[ComfyUI] 100%|██████████| 30/30 [02:45<00:00,  5.52s/it]
[ComfyUI] Prompt executed in 168.43 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

Examples

View more examples

Run time and cost

This model runs on Nvidia H100 GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.