import torch
from diffusers import DiffusionPipeline
from diffusers.utils import export_to_video
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("tencent/HunyuanVideo", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("strangerzonehf/Hunyuan-t2v-Cartoon-LoRA")
prompt = "cartoon motion real girl with messy bun and sparkling eyes, walking joyfully down a sunny, ivy-covered alley, holding a red heart. Striped dress, matching socks and sneakers. Soft sunlight, dreamy Pixar style, warm and whimsical atmosphere, cinematic depth of field."
output = pipe(prompt=prompt).frames[0]
export_to_video(output, "output.mp4")- Prompt
- cartoon motion real girl with messy bun and sparkling eyes, walking joyfully down a sunny, ivy-covered alley, holding a red heart. Striped dress, matching socks and sneakers. Soft sunlight, dreamy Pixar style, warm and whimsical atmosphere, cinematic depth of field.
Hunyuan-t2v-Cartoon-LoRA
Hunyuan-t2v-Cartoon-LoRA is a text-to-video adapter fine-tuned using human preferences. It is based on the tencent/HunyuanVideo text-to-video model and has been trained with 66 cartoon-style entries over 2,100 steps across 11 epochs.
Limitations
- Not suitable for complex indoor scenes
- Not recommended for robotic or animal characters
Trigger words
You should use cartoon motion to trigger the image generation.
You should use real to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 2
Model tree for strangerzonehf/Hunyuan-t2v-Cartoon-LoRA
Base model
tencent/HunyuanVideo