Pixar

Developed by Remade-AI

LoRA trained on Wan2.1 14B text-to-video model for generating Pixar-style animations

Text-to-Video EnglishOpen Source License:Apache-2.0 #Pixar animation style #Text-to-Video LoRA #Multi-object style consistency

Downloads 126

Release Time : 3/24/2025

Model Overview

This LoRA model is specifically designed for generating Pixar-style video content. Through style adaptation training on the base text-to-video model, it maintains stylistic consistency across different object types.

Model Features

Style consistency

Maintains unified Pixar animation style across different object types

Simple prompt structure

Generates stylized content using standardized trigger phrases

Community support

Provides Discord community support with free access and LoRA training requests

Model Capabilities

Text-to-video generation

Animation style conversion

Multi-object scene generation

Use Cases

Creative content generation

Short animation creation

Quickly generate Pixar-style short animation concepts

Sample videos demonstrate style consistency across various scenarios

Concept visualization

Transform text descriptions into stylized animation previews

Useful for pre-production concept development in film/TV

license: apache-2.0 language:

en base_model:
Wan-AI/Wan2.1-T2V-14B pipeline_tag: text-to-video tags:
text-to-video
text-to-image
lora
diffusers
template:diffusion-lora widget:
text: >- p1x4r_5ty13 Pixar animation style A small brown puppy with floppy ears sits on a grassy hill, tilting its head curiously at a floating dandelion seed drifting past. Its big, round eyes shine in the soft golden light of the setting sun. The background features rolling hills and a wooden fence. output: url: example_videos/pixar1.mp4
text: >- p1x4r_5ty13 Pixar animation style A robot is standing on a platform in space, looking at planet Earth. The planet is blue and green, with fluffy white clouds. output: url: example_videos/pixar2.mp4
text: >- p1x4r_5ty13 Pixar animation style A large, muscular, humanoid figure stands in front of a large wall of flowing lava. The figure is silhouetted against the bright orange and yellow glow of the lava. On each side of the lava wall, two tall, dark figures stand in a similar stance to the figure in the middle. The wall of lava is made of swirling, orange and yellow fluid that moves in a similar way to water. output: url: example_videos/pixar3.mp4
text: >- p1x4r_5ty13 Pixar animation style A young boy wearing a spacesuit stands on a small moon, staring in wonder at the massive planet hanging in the sky above. His helmet reflects the twinkling stars around him. Nearby, his tiny rover beeps softly as it scans a glowing rock. output: url: example_videos/pixar4.mp4

Pixar Animation Style LoRA for Wan2.1 14B T2V

Overview

This LoRA is trained on the Wan2.1 14B T2V model and allows you to generate videos in Pixar animation style!

Features

Trained on the Wan2.1 14B T2V base model
Consistent results across different object types
Simple prompt structure that's easy to adapt

Community

Discord: Join our community to generate videos with this LoRA for free
Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!

Model File and Inference Workflow

📥 Download Links:

pixar_10_epochs.safetensors - LoRA Model File
wan_txt2vid_lora_workflow.json - Wan T2V with LoRA Workflow for ComfyUI

Recommended Settings

LoRA Strength: 1.0
Embedded Guidance Scale: 6.0
Flow Shift: 5.0

Trigger Words

The key trigger phrase is: p1x4r_5ty13 Pixar animation style

Prompt Template

For prompting, check out the example prompts; this way of prompting seems to work very well.

ComfyUI Workflow

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

See the Downloads section above for the modified workflow.

Model Information

The model weights are available in Safetensors format. See the Downloads section above.

Training Details

Base Model: Wan2.1 14B T2V
Training Data: Trained on 4 minutes of video comprised of 47 short clips (each clip captioned separately) of various videos in Pixar animation style.
Epochs: 10