Steamboat Willie 14b

🚀 Steamboat Willie LoRA

This LoRA model enables text-to-video generation in the Steamboat Willie style of the golden era animation.

🚀 Quick Start

✨ Features

• Text-to-Video Generation: Generate videos based on text prompts in the Steamboat Willie style.
• LoRA Integration: Compatible with the Wan2.1-T2V series models.
• Multiple Hosting Platforms: Available on Hugging Face and CivitAI.

📦 Installation

To use this model with the diffusers library, you need to install the latest version from the GitHub repository:

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

💻 Usage Examples

Basic Usage

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)
pipe.scheduler = UniPCMultistepScheduler.from_config(
  pipe.scheduler.config,
  flow_shift=5.0
)
pipe.to("cuda")
pipe.load_lora_weights("benjamin-paine/steamboat-willie-14b")
pipe.enable_model_cpu_offload() # for low-vram environments

prompt = "steamboat willie style, golden era animation, an anthropomorphic cat character wearing a hat removes it and performs a courteous bow"
negative_prompt = "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走"
output = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    height=720,
    width=1280,
    num_frames=81,
    guidance_scale=5.0,
    num_inference_steps=32
).frames[0]
export_to_video(output, "output.mp4", fps=16)

📚 Documentation

Model Description

The model is trained on clips from Steamboat Willie, which are split by scene and captioned using Qwen2.5-VL-3B-Instruct. It is also available for Wan2.1-T2V-1.3B and additionally hosted on CivitAI.

Trigger Words

The model was trained with the trigger phrase "steamboat willie style". The best results are achieved when using this trigger phrase combined with "golden era animation".

📄 License

The model is released under the cc0-1.0 license.

📦 Download Model

The weights for this model are available in Safetensors format. You can download them from the Files & versions tab.

📋 Model Information

🚀 Widget Examples

You can try out the model using the following widget examples:

• Prompt: steamboat willie style, golden era animation, a stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots, and carries a black purse. She wears sunglasses and red lipstick. She walks confidently and casually. The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about.
  • Negative Prompt: 色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走
  • Output: videos/t2v-1.webp
• Prompt: steamboat willie style, golden era animation, close-up of a short fluffy monster kneeling beside a melting red candle. the mood is one of wonder and curiosity, as the monster gazes at the flame with wide eyes and open mouth. Its pose and expression convey a sense of innocence and playfulness, as if it is exploring the world around it for the first time. The use of warm colors and dramatic lighting further enhances the cozy atmosphere of the image.
  • Negative Prompt: 色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走
  • Output: videos/t2v-2.webp