惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

M
MIT News - Artificial intelligence
罗磊的独立博客
Hugging Face - Blog
Hugging Face - Blog
Apple Machine Learning Research
Apple Machine Learning Research
Last Week in AI
Last Week in AI
S
SegmentFault 最新的问题
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
美团技术团队
人人都是产品经理
人人都是产品经理
WordPress大学
WordPress大学
The Cloudflare Blog
IT之家
IT之家
雷峰网
雷峰网
小众软件
小众软件
博客园 - 叶小钗
博客园 - 聂微东
爱范儿
爱范儿
博客园 - 司徒正美
博客园 - 三生石上(FineUI控件)
V
Visual Studio Blog
博客园 - 【当耐特】
V
V2EX
博客园_首页
T
Tailwind CSS Blog

Replicate's blog

How to make remarkable videos with Seedance 2.0 – Replicate blog How to prompt Seedream 5.0 – Replicate blog Recraft V4: image generation with design taste – Replicate blog Run Isaac 0.1 on Replicate – Replicate blog Run FLUX.2 on Replicate – Replicate blog How to prompt Nano Banana Pro – Replicate blog Retro Diffusion's pixel art models are now on Replicate – Replicate blog Replicate is joining Cloudflare – Replicate blog Extract text from documents and images with Datalab Marker and OCR – Replicate blog How to prompt Veo 3.1 – Replicate blog IBM's Granite 4.0 is now on Replicate – Replicate blog Which image editing model should I use? – Replicate blog Introducing our new search API – Replicate blog Torch compile caching for inference speed – Replicate blog Announcing Replicate's remote MCP server – Replicate blog How to prompt Veo 3 with images – Replicate blog Open source video is back – Replicate blog Generate consistent characters – Replicate blog Bria is now on Replicate – Replicate blog How we optimized FLUX.1 Kontext [dev] – Replicate blog Compare AI video models – Replicate blog The FLUX.1 Kontext hackathon – Replicate blog How to prompt Veo 3 for the best results – Replicate blog Get the most from Google Veo 3 – Replicate blog FLUX.1 Kontext from the community – Replicate blog Use FLUX.1 Kontext to edit images with words – Replicate blog Generate incredible images with Google's Imagen 4 – Replicate blog Run OpenAI’s latest models on Replicate – Replicate blog NVIDIA H100 GPUs are here – Replicate blog Run 30,000+ LoRAs on Hugging Face with Replicate – Replicate blog
Stylized video with Wan2.1 – Replicate blog
2025-04-01 · via Replicate's blog

Wan 2.1 is a fast, open-source model for generating videos from text or images.

A particularly fun way to use Wan is for video style transfer. Whether you want to make dreamy Studio Ghibli-style loops, gritty cyberpunk trailers, or something entirely your own, Wan makes it easy to create stylized videos. You can start right away with a premade style, or train a custom one in minutes using your own images.

Replicate also supports fast inference with LoRAs on Wan 2.1, so you can apply styles to your videos with shorter wait times and no extra setup.

Here’s how you can get started.

Use a premade style

You can run premade styles on top of these two text-to-video Wan 2.1 models:

Wan 2.1 text to video, 480p

Wan 2.1 text to video, 720p

To use a style, type your prompt, set fast_mode to “Fast”, and add a link to your weights in the lora_weights input. This link can be any arbitrary safetensors URL from the internet — from HuggingFace, CivitAI, or any other platform.

The lora_weights field even accepts finetuned Wan models you find on Replicate. Here’s an example with fofr/wan-14b-cyberpunk-realistic using Replicate’s Python client:

Here are a few premade styles you can try out:

Create Your Own Style

On Replicate, you can also train Wan on photos that you curate to create your own stylized videos. Here’s how using ostris/wan-lora-trainer.

  1. Pick a destination model (or type a new name to create one).
  2. Prepare your training images. Make a folder with at least 25 images that reflect your style, then zip the folder.
  3. Upload the zip file to the input_images field.
  4. Choose a trigger_word — this is what you’ll type in your prompt to activate the style.
  5. Keep autocaption turned on. You can optionally add an autocaption_prefix or autocaption_suffix to guide the style more.
  6. Leave the other settings as-is (or tweak them if you want), then click Run.

In a few minutes, you’ll have your own version of Wan, trained on your style and ready to generate videos.

Whether you use a premade style or train your own, Wan 2.1 makes it simple to create stylized video that feels uniquely yours. Just pick a style, write a prompt, and hit run.

Share what you make on our Discord or tag us on X! We’re reposting our favorites.