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

fofr / wan-14b-cyberpunk-realistic

Wan2.1 fine tuned on hyper realistic Cyberpunk 2077 mods

Cold

Public
65 runs
H100

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

in the style of CYB77, driving a car very fast through a city at nightin the style of CYB77, driving a car very fast through a city at night

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-cyberpunk-realistic

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-cyberpunk-realistic 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-cyberpunk-realistic:8d934a800aee769933dd3f54c9348ac92d28c588065389ce7a526c77150069b5",
  {
    input: {
      image: "https://replicate.delivery/xezq/cPbpoOia6exgEq9sTwWMn9HsytppiVjq3cYrfYfzErlfqqsRB/tmpr4czcw2e.png",
      frames: 81,
      prompt: "in the style of CYB77, driving a car very fast through a city at night",
      fast_mode: "Off",
      resolution: "480p",
      aspect_ratio: "16:9",
      sample_shift: 8,
      sample_steps: 50,
      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-cyberpunk-realistic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/wan-14b-cyberpunk-realistic:8d934a800aee769933dd3f54c9348ac92d28c588065389ce7a526c77150069b5",
    input={
        "image": "https://replicate.delivery/xezq/cPbpoOia6exgEq9sTwWMn9HsytppiVjq3cYrfYfzErlfqqsRB/tmpr4czcw2e.png",
        "frames": 81,
        "prompt": "in the style of CYB77, driving a car very fast through a city at night",
        "fast_mode": "Off",
        "resolution": "480p",
        "aspect_ratio": "16:9",
        "sample_shift": 8,
        "sample_steps": 50,
        "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-cyberpunk-realistic 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-cyberpunk-realistic:8d934a800aee769933dd3f54c9348ac92d28c588065389ce7a526c77150069b5",
    "input": {
      "image": "https://replicate.delivery/xezq/cPbpoOia6exgEq9sTwWMn9HsytppiVjq3cYrfYfzErlfqqsRB/tmpr4czcw2e.png",
      "frames": 81,
      "prompt": "in the style of CYB77, driving a car very fast through a city at night",
      "fast_mode": "Off",
      "resolution": "480p",
      "aspect_ratio": "16:9",
      "sample_shift": 8,
      "sample_steps": 50,
      "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-cyberpunk-realistic@sha256:8d934a800aee769933dd3f54c9348ac92d28c588065389ce7a526c77150069b5 \
  -i 'image="https://replicate.delivery/xezq/cPbpoOia6exgEq9sTwWMn9HsytppiVjq3cYrfYfzErlfqqsRB/tmpr4czcw2e.png"' \
  -i 'frames=81' \
  -i 'prompt="in the style of CYB77, driving a car very fast through a city at night"' \
  -i 'fast_mode="Off"' \
  -i 'resolution="480p"' \
  -i 'aspect_ratio="16:9"' \
  -i 'sample_shift=8' \
  -i 'sample_steps=50' \
  -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-cyberpunk-realistic@sha256:8d934a800aee769933dd3f54c9348ac92d28c588065389ce7a526c77150069b5
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "image": "https://replicate.delivery/xezq/cPbpoOia6exgEq9sTwWMn9HsytppiVjq3cYrfYfzErlfqqsRB/tmpr4czcw2e.png",
      "frames": 81,
      "prompt": "in the style of CYB77, driving a car very fast through a city at night",
      "fast_mode": "Off",
      "resolution": "480p",
      "aspect_ratio": "16:9",
      "sample_shift": 8,
      "sample_steps": 50,
      "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": "2025-03-22T18:10:33.973403Z",
  "created_at": "2025-03-22T18:01:50.089000Z",
  "data_removed": false,
  "error": null,
  "id": "5hpne6xf15rme0cnqw2933vxr0",
  "input": {
    "image": "https://replicate.delivery/xezq/cPbpoOia6exgEq9sTwWMn9HsytppiVjq3cYrfYfzErlfqqsRB/tmpr4czcw2e.png",
    "frames": 81,
    "prompt": "in the style of CYB77, driving a car very fast through a city at night",
    "fast_mode": "Off",
    "resolution": "480p",
    "aspect_ratio": "16:9",
    "sample_shift": 8,
    "sample_steps": 50,
    "negative_prompt": "",
    "lora_strength_clip": 1,
    "sample_guide_scale": 5,
    "lora_strength_model": 1
  },
  "logs": "Random seed set to: 1974571946\n✅ 14b_035cb393b31bb26f95fdf77699f31f97.safetensors already cached\nChecking inputs\n✅ /tmp/inputs/image.png\n====================================\nChecking weights\n✅ clip_vision_h.safetensors exists in ComfyUI/models/clip_vision\n✅ 14b_035cb393b31bb26f95fdf77699f31f97.safetensors exists in loras directory\n✅ umt5_xxl_fp16.safetensors exists in ComfyUI/models/text_encoders\n✅ wan2.1_i2v_480p_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 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 59, title: CLIP Vision Encode, class type: CLIPVisionEncode\nExecuting node 6, title: CLIP Text Encode (Positive Prompt), class type: CLIPTextEncode\nExecuting node 58, title: WanImageToVideo, class type: WanImageToVideo\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]\n[ComfyUI] 0%|          | 0/50 [00:00<?, ?it/s]\n[ComfyUI] 2%|▏         | 1/50 [00:08<06:41,  8.19s/it]\n[ComfyUI] 4%|▍         | 2/50 [00:18<07:33,  9.45s/it]\n[ComfyUI] 6%|▌         | 3/50 [00:28<07:43,  9.86s/it]\n[ComfyUI] 8%|▊         | 4/50 [00:39<07:42, 10.06s/it]\n[ComfyUI] 10%|█         | 5/50 [00:49<07:38, 10.18s/it]\n[ComfyUI] 12%|█▏        | 6/50 [01:00<07:31, 10.26s/it]\n[ComfyUI] 14%|█▍        | 7/50 [01:10<07:23, 10.30s/it]\n[ComfyUI] 16%|█▌        | 8/50 [01:20<07:13, 10.33s/it]\n[ComfyUI] 18%|█▊        | 9/50 [01:31<07:04, 10.36s/it]\n[ComfyUI] 20%|██        | 10/50 [01:41<06:54, 10.37s/it]\n[ComfyUI] 22%|██▏       | 11/50 [01:52<06:44, 10.38s/it]\n[ComfyUI] 24%|██▍       | 12/50 [02:02<06:34, 10.38s/it]\n[ComfyUI] 26%|██▌       | 13/50 [02:12<06:24, 10.39s/it]\n[ComfyUI] 28%|██▊       | 14/50 [02:23<06:14, 10.39s/it]\n[ComfyUI] 30%|███       | 15/50 [02:33<06:03, 10.40s/it]\n[ComfyUI] 32%|███▏      | 16/50 [02:44<05:53, 10.39s/it]\n[ComfyUI] 34%|███▍      | 17/50 [02:54<05:43, 10.40s/it]\n[ComfyUI] 36%|███▌      | 18/50 [03:04<05:32, 10.40s/it]\n[ComfyUI] 38%|███▊      | 19/50 [03:15<05:22, 10.40s/it]\n[ComfyUI] 40%|████      | 20/50 [03:25<05:11, 10.40s/it]\n[ComfyUI] 42%|████▏     | 21/50 [03:36<05:01, 10.40s/it]\n[ComfyUI] 44%|████▍     | 22/50 [03:46<04:51, 10.40s/it]\n[ComfyUI] 46%|████▌     | 23/50 [03:56<04:40, 10.40s/it]\n[ComfyUI] 48%|████▊     | 24/50 [04:07<04:30, 10.40s/it]\n[ComfyUI] 50%|█████     | 25/50 [04:17<04:19, 10.40s/it]\n[ComfyUI] 52%|█████▏    | 26/50 [04:28<04:09, 10.40s/it]\n[ComfyUI] 54%|█████▍    | 27/50 [04:38<03:59, 10.40s/it]\n[ComfyUI] 56%|█████▌    | 28/50 [04:48<03:48, 10.40s/it]\n[ComfyUI] 58%|█████▊    | 29/50 [04:59<03:38, 10.40s/it]\n[ComfyUI] 60%|██████    | 30/50 [05:09<03:27, 10.40s/it]\n[ComfyUI] 62%|██████▏   | 31/50 [05:20<03:17, 10.41s/it]\n[ComfyUI] 64%|██████▍   | 32/50 [05:30<03:07, 10.41s/it]\n[ComfyUI] 66%|██████▌   | 33/50 [05:40<02:56, 10.40s/it]\n[ComfyUI] 68%|██████▊   | 34/50 [05:51<02:46, 10.40s/it]\n[ComfyUI] 70%|███████   | 35/50 [06:01<02:36, 10.40s/it]\n[ComfyUI] 72%|███████▏  | 36/50 [06:12<02:25, 10.40s/it]\n[ComfyUI] 74%|███████▍  | 37/50 [06:22<02:15, 10.40s/it]\n[ComfyUI] 76%|███████▌  | 38/50 [06:32<02:04, 10.40s/it]\n[ComfyUI] 78%|███████▊  | 39/50 [06:43<01:54, 10.40s/it]\n[ComfyUI] 80%|████████  | 40/50 [06:53<01:43, 10.40s/it]\n[ComfyUI] 82%|████████▏ | 41/50 [07:04<01:33, 10.40s/it]\n[ComfyUI] 84%|████████▍ | 42/50 [07:14<01:23, 10.40s/it]\n[ComfyUI] 86%|████████▌ | 43/50 [07:24<01:12, 10.38s/it]\n[ComfyUI] 88%|████████▊ | 44/50 [07:35<01:02, 10.38s/it]\n[ComfyUI] 90%|█████████ | 45/50 [07:45<00:51, 10.37s/it]\n[ComfyUI] 92%|█████████▏| 46/50 [07:55<00:41, 10.36s/it]\n[ComfyUI] 94%|█████████▍| 47/50 [08:06<00:31, 10.36s/it]\n[ComfyUI] 96%|█████████▌| 48/50 [08:16<00:20, 10.36s/it]\n[ComfyUI] 98%|█████████▊| 49/50 [08:26<00:10, 10.35s/it]\n[ComfyUI] 100%|██████████| 50/50 [08:39<00:00, 10.98s/it]\nExecuting node 8, title: VAE Decode, class type: VAEDecode\nExecuting node 50, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] 100%|██████████| 50/50 [08:39<00:00, 10.39s/it]\n[ComfyUI] Prompt executed in 523.56 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": 523.874907465,
    "total_time": 523.884403
  },
  "output": [
    "https://replicate.delivery/xezq/asl3HD14zJpjCV3WAefO5cMDOqyxKG2ZWIfN1dD9DRby4V2oA/R8_Wan_00001.mp4"
  ],
  "started_at": "2025-03-22T18:01:50.098496Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-jmoxhihcrorvklnco5opfvpvphgxi32yv3krfmmay5wugh4h45lq",
    "get": "https://api.replicate.com/v1/predictions/5hpne6xf15rme0cnqw2933vxr0",
    "cancel": "https://api.replicate.com/v1/predictions/5hpne6xf15rme0cnqw2933vxr0/cancel"
  },
  "version": "8d934a800aee769933dd3f54c9348ac92d28c588065389ce7a526c77150069b5"
}

Generated in

8 minutes 44 seconds

Tweak it ShareReport

Random seed set to: 1974571946
✅ 14b_035cb393b31bb26f95fdf77699f31f97.safetensors already cached
Checking inputs
✅ /tmp/inputs/image.png
====================================
Checking weights
✅ clip_vision_h.safetensors exists in ComfyUI/models/clip_vision
✅ 14b_035cb393b31bb26f95fdf77699f31f97.safetensors exists in loras directory
✅ umt5_xxl_fp16.safetensors exists in ComfyUI/models/text_encoders
✅ wan2.1_i2v_480p_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 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 59, title: CLIP Vision Encode, class type: CLIPVisionEncode
Executing node 6, title: CLIP Text Encode (Positive Prompt), class type: CLIPTextEncode
Executing node 58, title: WanImageToVideo, class type: WanImageToVideo
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]
[ComfyUI] 0%|          | 0/50 [00:00<?, ?it/s]
[ComfyUI] 2%|▏         | 1/50 [00:08<06:41,  8.19s/it]
[ComfyUI] 4%|▍         | 2/50 [00:18<07:33,  9.45s/it]
[ComfyUI] 6%|▌         | 3/50 [00:28<07:43,  9.86s/it]
[ComfyUI] 8%|▊         | 4/50 [00:39<07:42, 10.06s/it]
[ComfyUI] 10%|█         | 5/50 [00:49<07:38, 10.18s/it]
[ComfyUI] 12%|█▏        | 6/50 [01:00<07:31, 10.26s/it]
[ComfyUI] 14%|█▍        | 7/50 [01:10<07:23, 10.30s/it]
[ComfyUI] 16%|█▌        | 8/50 [01:20<07:13, 10.33s/it]
[ComfyUI] 18%|█▊        | 9/50 [01:31<07:04, 10.36s/it]
[ComfyUI] 20%|██        | 10/50 [01:41<06:54, 10.37s/it]
[ComfyUI] 22%|██▏       | 11/50 [01:52<06:44, 10.38s/it]
[ComfyUI] 24%|██▍       | 12/50 [02:02<06:34, 10.38s/it]
[ComfyUI] 26%|██▌       | 13/50 [02:12<06:24, 10.39s/it]
[ComfyUI] 28%|██▊       | 14/50 [02:23<06:14, 10.39s/it]
[ComfyUI] 30%|███       | 15/50 [02:33<06:03, 10.40s/it]
[ComfyUI] 32%|███▏      | 16/50 [02:44<05:53, 10.39s/it]
[ComfyUI] 34%|███▍      | 17/50 [02:54<05:43, 10.40s/it]
[ComfyUI] 36%|███▌      | 18/50 [03:04<05:32, 10.40s/it]
[ComfyUI] 38%|███▊      | 19/50 [03:15<05:22, 10.40s/it]
[ComfyUI] 40%|████      | 20/50 [03:25<05:11, 10.40s/it]
[ComfyUI] 42%|████▏     | 21/50 [03:36<05:01, 10.40s/it]
[ComfyUI] 44%|████▍     | 22/50 [03:46<04:51, 10.40s/it]
[ComfyUI] 46%|████▌     | 23/50 [03:56<04:40, 10.40s/it]
[ComfyUI] 48%|████▊     | 24/50 [04:07<04:30, 10.40s/it]
[ComfyUI] 50%|█████     | 25/50 [04:17<04:19, 10.40s/it]
[ComfyUI] 52%|█████▏    | 26/50 [04:28<04:09, 10.40s/it]
[ComfyUI] 54%|█████▍    | 27/50 [04:38<03:59, 10.40s/it]
[ComfyUI] 56%|█████▌    | 28/50 [04:48<03:48, 10.40s/it]
[ComfyUI] 58%|█████▊    | 29/50 [04:59<03:38, 10.40s/it]
[ComfyUI] 60%|██████    | 30/50 [05:09<03:27, 10.40s/it]
[ComfyUI] 62%|██████▏   | 31/50 [05:20<03:17, 10.41s/it]
[ComfyUI] 64%|██████▍   | 32/50 [05:30<03:07, 10.41s/it]
[ComfyUI] 66%|██████▌   | 33/50 [05:40<02:56, 10.40s/it]
[ComfyUI] 68%|██████▊   | 34/50 [05:51<02:46, 10.40s/it]
[ComfyUI] 70%|███████   | 35/50 [06:01<02:36, 10.40s/it]
[ComfyUI] 72%|███████▏  | 36/50 [06:12<02:25, 10.40s/it]
[ComfyUI] 74%|███████▍  | 37/50 [06:22<02:15, 10.40s/it]
[ComfyUI] 76%|███████▌  | 38/50 [06:32<02:04, 10.40s/it]
[ComfyUI] 78%|███████▊  | 39/50 [06:43<01:54, 10.40s/it]
[ComfyUI] 80%|████████  | 40/50 [06:53<01:43, 10.40s/it]
[ComfyUI] 82%|████████▏ | 41/50 [07:04<01:33, 10.40s/it]
[ComfyUI] 84%|████████▍ | 42/50 [07:14<01:23, 10.40s/it]
[ComfyUI] 86%|████████▌ | 43/50 [07:24<01:12, 10.38s/it]
[ComfyUI] 88%|████████▊ | 44/50 [07:35<01:02, 10.38s/it]
[ComfyUI] 90%|█████████ | 45/50 [07:45<00:51, 10.37s/it]
[ComfyUI] 92%|█████████▏| 46/50 [07:55<00:41, 10.36s/it]
[ComfyUI] 94%|█████████▍| 47/50 [08:06<00:31, 10.36s/it]
[ComfyUI] 96%|█████████▌| 48/50 [08:16<00:20, 10.36s/it]
[ComfyUI] 98%|█████████▊| 49/50 [08:26<00:10, 10.35s/it]
[ComfyUI] 100%|██████████| 50/50 [08:39<00:00, 10.98s/it]
Executing node 8, title: VAE Decode, class type: VAEDecode
Executing node 50, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine
[ComfyUI] 100%|██████████| 50/50 [08:39<00:00, 10.39s/it]
[ComfyUI] Prompt executed in 523.56 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