fofr/wan-14b-laezel – Run with an API on Replicate

fofr / wan-14b-laezel

Wan2.1 14b fine-tuned on the Baldur's Gate 3 character Laezel

Cold

Public
13 runs
H100
Weights

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

a scene where LAEZEL is laughing in a cafe, warm, bokeh, fireplacea scene where LAEZEL is laughing in a cafe, warm, bokeh, fireplace

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=fofr/wan-14b-laezel

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";
import fs from "node:fs";

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

Run fofr/wan-14b-laezel using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fofr/wan-14b-laezel:47f42ccb2ed4659754ba103fb0c915d0cce85532af6137fc68a2375eb4c60480",
  {
    input: {
      frames: 81,
      prompt: "a scene where LAEZEL is laughing in a cafe, warm, bokeh, fireplace",
      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 fofr/wan-14b-laezel using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/wan-14b-laezel:47f42ccb2ed4659754ba103fb0c915d0cce85532af6137fc68a2375eb4c60480",
    input={
        "frames": 81,
        "prompt": "a scene where LAEZEL is laughing in a cafe, warm, bokeh, fireplace",
        "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 fofr/wan-14b-laezel 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": "fofr/wan-14b-laezel:47f42ccb2ed4659754ba103fb0c915d0cce85532af6137fc68a2375eb4c60480",
    "input": {
      "frames": 81,
      "prompt": "a scene where LAEZEL is laughing in a cafe, warm, bokeh, fireplace",
      "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/fofr/wan-14b-laezel@sha256:47f42ccb2ed4659754ba103fb0c915d0cce85532af6137fc68a2375eb4c60480 \
  -i 'frames=81' \
  -i 'prompt="a scene where LAEZEL is laughing in a cafe, warm, bokeh, fireplace"' \
  -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/fofr/wan-14b-laezel@sha256:47f42ccb2ed4659754ba103fb0c915d0cce85532af6137fc68a2375eb4c60480
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "frames": 81,
      "prompt": "a scene where LAEZEL is laughing in a cafe, warm, bokeh, fireplace",
      "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": "2025-03-12T12:36:44.307655Z",
  "created_at": "2025-03-12T12:33:53.647000Z",
  "data_removed": false,
  "error": null,
  "id": "92adzpesxxrma0cnh9c8ngah6c",
  "input": {
    "frames": 81,
    "prompt": "a scene where LAEZEL is laughing in a cafe, warm, bokeh, fireplace",
    "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: 1997690228\n✅ 49be09c47a6472548969c7eb1d45d1b9.safetensors already cached\nChecking inputs\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✅ 49be09c47a6472548969c7eb1d45d1b9.safetensors exists in loras directory\n✅ wan2.1_t2v_14B_bf16.safetensors exists in ComfyUI/models/diffusion_models\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 [00:07<03:28,  7.20s/it]\n[ComfyUI] 7%|▋         | 2/30 [00:16<04:00,  8.59s/it]\n[ComfyUI] 10%|█         | 3/30 [00:26<04:03,  9.02s/it]\n[ComfyUI] TeaCache: Initialized\n[ComfyUI]\n[ComfyUI] 13%|█▎        | 4/30 [00:38<04:26, 10.26s/it]\n[ComfyUI] 20%|██        | 6/30 [00:48<02:58,  7.45s/it]\n[ComfyUI] 27%|██▋       | 8/30 [00:58<02:20,  6.38s/it]\n[ComfyUI] 33%|███▎      | 10/30 [01:08<01:56,  5.84s/it]\n[ComfyUI] 40%|████      | 12/30 [01:18<01:39,  5.53s/it]\n[ComfyUI] 47%|████▋     | 14/30 [01:28<01:25,  5.34s/it]\n[ComfyUI] 53%|█████▎    | 16/30 [01:38<01:13,  5.22s/it]\n[ComfyUI] 60%|██████    | 18/30 [01:48<01:01,  5.15s/it]\n[ComfyUI] 67%|██████▋   | 20/30 [01:57<00:50,  5.10s/it]\n[ComfyUI] 73%|███████▎  | 22/30 [02:07<00:40,  5.06s/it]\n[ComfyUI] 80%|████████  | 24/30 [02:17<00:30,  5.04s/it]\n[ComfyUI] 87%|████████▋ | 26/30 [02:27<00:20,  5.02s/it]\n[ComfyUI] 93%|█████████▎| 28/30 [02:37<00:10,  5.01s/it]\n[ComfyUI] 100%|██████████| 30/30 [02:47<00:00,  5.00s/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 [02:47<00:00,  5.59s/it]\n[ComfyUI] Prompt executed in 170.48 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": 170.654119001,
    "total_time": 170.660655
  },
  "output": [
    "https://replicate.delivery/xezq/i9enM2xXXNT1Siglhh15IvZvpoMRlytk2sqegWUz6rpcHzXUA/R8_Wan_00001.mp4"
  ],
  "started_at": "2025-03-12T12:33:53.653536Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-iif4acjobgfu74d7pkvjaocmk5qnkdslud4d4td3i4pegaoczzfa",
    "get": "https://api.replicate.com/v1/predictions/92adzpesxxrma0cnh9c8ngah6c",
    "cancel": "https://api.replicate.com/v1/predictions/92adzpesxxrma0cnh9c8ngah6c/cancel"
  },
  "version": "47f42ccb2ed4659754ba103fb0c915d0cce85532af6137fc68a2375eb4c60480"
}

Generated in

2 minutes 51 seconds

Tweak it ShareReport

Random seed set to: 1997690228
✅ 49be09c47a6472548969c7eb1d45d1b9.safetensors already cached
Checking inputs
====================================
Checking weights
✅ wan_2.1_vae.safetensors exists in ComfyUI/models/vae
✅ umt5_xxl_fp16.safetensors exists in ComfyUI/models/text_encoders
✅ 49be09c47a6472548969c7eb1d45d1b9.safetensors exists in loras directory
✅ wan2.1_t2v_14B_bf16.safetensors exists in ComfyUI/models/diffusion_models
====================================
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 [00:07<03:28,  7.20s/it]
[ComfyUI] 7%|▋         | 2/30 [00:16<04:00,  8.59s/it]
[ComfyUI] 10%|█         | 3/30 [00:26<04:03,  9.02s/it]
[ComfyUI] TeaCache: Initialized
[ComfyUI]
[ComfyUI] 13%|█▎        | 4/30 [00:38<04:26, 10.26s/it]
[ComfyUI] 20%|██        | 6/30 [00:48<02:58,  7.45s/it]
[ComfyUI] 27%|██▋       | 8/30 [00:58<02:20,  6.38s/it]
[ComfyUI] 33%|███▎      | 10/30 [01:08<01:56,  5.84s/it]
[ComfyUI] 40%|████      | 12/30 [01:18<01:39,  5.53s/it]
[ComfyUI] 47%|████▋     | 14/30 [01:28<01:25,  5.34s/it]
[ComfyUI] 53%|█████▎    | 16/30 [01:38<01:13,  5.22s/it]
[ComfyUI] 60%|██████    | 18/30 [01:48<01:01,  5.15s/it]
[ComfyUI] 67%|██████▋   | 20/30 [01:57<00:50,  5.10s/it]
[ComfyUI] 73%|███████▎  | 22/30 [02:07<00:40,  5.06s/it]
[ComfyUI] 80%|████████  | 24/30 [02:17<00:30,  5.04s/it]
[ComfyUI] 87%|████████▋ | 26/30 [02:27<00:20,  5.02s/it]
[ComfyUI] 93%|█████████▎| 28/30 [02:37<00:10,  5.01s/it]
[ComfyUI] 100%|██████████| 30/30 [02:47<00:00,  5.00s/it]
Executing node 8, title: VAE Decode, class type: VAEDecode
Executing node 50, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine
[ComfyUI] 100%|██████████| 30/30 [02:47<00:00,  5.59s/it]
[ComfyUI] Prompt executed in 170.48 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