Wan 14b Cyberpunk Realistic

🚀 Wan 14B Cyberpunk Realistic (image-to-video)

This is a LoRA for the Wan2.1 14b video generation model, enabling video generation in a specific style.

🚀 Quick Start

This LoRA can be used with diffusers or ComfyUI, and can be loaded against both the text - to - video and image - to - video Wan2.1 models.

✨ Features

About this LoRA

This is a LoRA for the Wan2.1 14b video generation model. It can be used with diffusers or ComfyUI, and can be loaded against both the text - to - video and image - to - video Wan2.1 models. It was trained on Replicate using AI toolkit: https://replicate.com/ostris/wan-lora-trainer/train

Trigger words

You should use CYB77 or "In the style of CYB77" to trigger the video generation.

Use this LoRA

Replicate has a collection of Wan2.1 models that are optimised for speed and cost. They can also be used with this LoRA:

• https://replicate.com/collections/wan-video
• https://replicate.com/fofr/wan2.1-with-lora

💻 Usage Examples

Basic Usage

Run this LoRA with an API using Replicate

import replicate

input = {
    "prompt": "CYB77",
    "image": "https://replicate.delivery/xezq/4BGR8w4ELvJfcqIG4KIF0Kr82JxtfQCM2xVAIUieSeifmTZjC/output_frame.jpg",
    "lora_url": "https://huggingface.co/fofr/wan-14b-cyberpunk-realistic/resolve/main/wan-14b-i2v-cyberpunk-realistic-lora.safetensors"
}

output = replicate.run(
    "fofr/wan2.1-with-lora:f83b84064136a38415a3aff66c326f94c66859b8ad7a2cb432e2822774f07b08",
    model="14b",
    input=input
)
for index, item in enumerate(output):
    with open(f"output_{index}.mp4", "wb") as file:
        file.write(item.read())

Using with Diffusers

pip install git+https://github.com/huggingface/diffusers.git

import torch
from diffusers.utils import export_to_video
from diffusers import AutoencoderKLWan, WanPipeline
from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler

model_id = "Wan-AI/Wan2.1-T2V-14B-Diffusers"
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanPipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
flow_shift = 3.0  # 5.0 for 720P, 3.0 for 480P
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=flow_shift)
pipe.to("cuda")

pipe.load_lora_weights("fofr/wan-14b-cyberpunk-realistic")

pipe.enable_model_cpu_offload() #for low-vram environments

prompt = "CYB77"
negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"

output = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    height=480,
    width=832,
    num_frames=81,
    guidance_scale=5.0,
).frames[0]
export_to_video(output, "output.mp4", fps=16)

🔧 Technical Details

• Steps: 5000
• Learning rate: 0.0001
• LoRA rank: 32

📚 Documentation

You can use the community tab to add videos that show off what you’ve made with this LoRA.

📄 License

This project is licensed under the Apache - 2.0 license.