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

fofr / wan-14b-black-sclera

Cold

Public
17 runs
H100

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

an extreme close up of an epic cyberpunk woman with BLACK_SCLERAan extreme close up of an epic cyberpunk woman with BLACK_SCLERA

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-black-sclera

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 fofr/wan-14b-black-sclera 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-black-sclera:a29fdf2f027f9978cc63160fc12851b2ca8fcf09e6ecbe94a60c30333fc6bc8d",
  {
    input: {
      frames: 81,
      prompt: "an extreme close up of an epic cyberpunk woman with BLACK_SCLERA",
      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
    }
  }
);
console.log(output);

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-black-sclera using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/wan-14b-black-sclera:a29fdf2f027f9978cc63160fc12851b2ca8fcf09e6ecbe94a60c30333fc6bc8d",
    input={
        "frames": 81,
        "prompt": "an extreme close up of an epic cyberpunk woman with BLACK_SCLERA",
        "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-black-sclera 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": "a29fdf2f027f9978cc63160fc12851b2ca8fcf09e6ecbe94a60c30333fc6bc8d",
    "input": {
      "frames": 81,
      "prompt": "an extreme close up of an epic cyberpunk woman with BLACK_SCLERA",
      "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.

Output

{
  "completed_at": "2025-03-12T14:13:21.812331Z",
  "created_at": "2025-03-12T14:10:31.743000Z",
  "data_removed": false,
  "error": null,
  "id": "015ejtajqxrmc0cnhartgbqs9r",
  "input": {
    "frames": 81,
    "prompt": "an extreme close up of an epic cyberpunk woman with BLACK_SCLERA",
    "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: 1914704925\n✅ c85289c3e6d294a5c361f58b843a0eec.safetensors already cached\nChecking inputs\n====================================\nChecking weights\n✅ wan_2.1_vae.safetensors exists in ComfyUI/models/vae\n✅ c85289c3e6d294a5c361f58b843a0eec.safetensors exists in loras directory\n✅ wan2.1_t2v_14B_bf16.safetensors exists in ComfyUI/models/diffusion_models\n✅ umt5_xxl_fp16.safetensors exists in ComfyUI/models/text_encoders\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<03:26,  7.11s/it]\n[ComfyUI] 7%|▋         | 2/30 [00:16<03:56,  8.45s/it]\n[ComfyUI] 10%|█         | 3/30 [00:25<04:00,  8.89s/it]\n[ComfyUI] TeaCache: Initialized\n[ComfyUI]\n[ComfyUI] 13%|█▎        | 4/30 [00:37<04:23, 10.14s/it]\n[ComfyUI] 20%|██        | 6/30 [00:47<02:57,  7.40s/it]\n[ComfyUI] 27%|██▋       | 8/30 [00:57<02:19,  6.35s/it]\n[ComfyUI] 33%|███▎      | 10/30 [01:07<01:56,  5.83s/it]\n[ComfyUI] 37%|███▋      | 11/30 [01:07<01:27,  4.60s/it]\n[ComfyUI] 40%|████      | 12/30 [01:17<01:44,  5.81s/it]\n[ComfyUI] 47%|████▋     | 14/30 [01:27<01:27,  5.48s/it]\n[ComfyUI] 53%|█████▎    | 16/30 [01:37<01:13,  5.28s/it]\n[ComfyUI] 60%|██████    | 18/30 [01:47<01:02,  5.17s/it]\n[ComfyUI] 67%|██████▋   | 20/30 [01:57<00:50,  5.09s/it]\n[ComfyUI] 73%|███████▎  | 22/30 [02:07<00:40,  5.05s/it]\n[ComfyUI] 80%|████████  | 24/30 [02:17<00:30,  5.03s/it]\n[ComfyUI] 87%|████████▋ | 26/30 [02:27<00:19,  5.00s/it]\n[ComfyUI] 93%|█████████▎| 28/30 [02:36<00:09,  4.99s/it]\n[ComfyUI] 97%|█████████▋| 29/30 [02:37<00:04,  4.12s/it]\n[ComfyUI] 100%|██████████| 30/30 [02:46<00:00,  5.29s/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 [02:46<00:00,  5.57s/it]\n[ComfyUI] Prompt executed in 169.86 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": 170.063121666,
    "total_time": 170.069331
  },
  "output": [
    "https://replicate.delivery/xezq/e8VdU9mDapQXVKyPgYgmBQ8HuLx7dYVSBD3EWFTmyhwAR6LKA/R8_Wan_00001.mp4"
  ],
  "started_at": "2025-03-12T14:10:31.749209Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-tnbeohl2s3uqv2ct34xy22eizwwjzbjjkz5sj3xruzfj4izryjeq",
    "get": "https://api.replicate.com/v1/predictions/015ejtajqxrmc0cnhartgbqs9r",
    "cancel": "https://api.replicate.com/v1/predictions/015ejtajqxrmc0cnhartgbqs9r/cancel"
  },
  "version": "a29fdf2f027f9978cc63160fc12851b2ca8fcf09e6ecbe94a60c30333fc6bc8d"
}

Generated in

2 minutes 50 seconds

Tweak it ShareReport

Random seed set to: 1914704925
✅ c85289c3e6d294a5c361f58b843a0eec.safetensors already cached
Checking inputs
====================================
Checking weights
✅ wan_2.1_vae.safetensors exists in ComfyUI/models/vae
✅ c85289c3e6d294a5c361f58b843a0eec.safetensors exists in loras directory
✅ wan2.1_t2v_14B_bf16.safetensors exists in ComfyUI/models/diffusion_models
✅ umt5_xxl_fp16.safetensors exists in ComfyUI/models/text_encoders
====================================
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<03:26,  7.11s/it]
[ComfyUI] 7%|▋         | 2/30 [00:16<03:56,  8.45s/it]
[ComfyUI] 10%|█         | 3/30 [00:25<04:00,  8.89s/it]
[ComfyUI] TeaCache: Initialized
[ComfyUI]
[ComfyUI] 13%|█▎        | 4/30 [00:37<04:23, 10.14s/it]
[ComfyUI] 20%|██        | 6/30 [00:47<02:57,  7.40s/it]
[ComfyUI] 27%|██▋       | 8/30 [00:57<02:19,  6.35s/it]
[ComfyUI] 33%|███▎      | 10/30 [01:07<01:56,  5.83s/it]
[ComfyUI] 37%|███▋      | 11/30 [01:07<01:27,  4.60s/it]
[ComfyUI] 40%|████      | 12/30 [01:17<01:44,  5.81s/it]
[ComfyUI] 47%|████▋     | 14/30 [01:27<01:27,  5.48s/it]
[ComfyUI] 53%|█████▎    | 16/30 [01:37<01:13,  5.28s/it]
[ComfyUI] 60%|██████    | 18/30 [01:47<01:02,  5.17s/it]
[ComfyUI] 67%|██████▋   | 20/30 [01:57<00:50,  5.09s/it]
[ComfyUI] 73%|███████▎  | 22/30 [02:07<00:40,  5.05s/it]
[ComfyUI] 80%|████████  | 24/30 [02:17<00:30,  5.03s/it]
[ComfyUI] 87%|████████▋ | 26/30 [02:27<00:19,  5.00s/it]
[ComfyUI] 93%|█████████▎| 28/30 [02:36<00:09,  4.99s/it]
[ComfyUI] 97%|█████████▋| 29/30 [02:37<00:04,  4.12s/it]
[ComfyUI] 100%|██████████| 30/30 [02:46<00:00,  5.29s/it]
Executing node 8, title: VAE Decode, class type: VAEDecode
Executing node 50, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine
[ComfyUI] 100%|██████████| 30/30 [02:46<00:00,  5.57s/it]
[ComfyUI] Prompt executed in 169.86 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.