svjack/Miuna_Shiodome_wan_2_1_1_3_B_text2video_lora

Miuna_Shiodome Text-to-Video Generation

This repository contains the necessary steps and scripts to generate videos using the Miuna_Shiodome text-to-video model. The model leverages LoRA (Low-Rank Adaptation) weights and pre-trained components to create high-quality anime-style videos based on textual prompts.

Prerequisites

Before proceeding, ensure that you have the following installed on your system:

• Ubuntu (or a compatible Linux distribution) • Python 3.x • pip (Python package manager) • Git • Git LFS (Git Large File Storage) • FFmpeg

Installation

1. Update and Install Dependencies

   sudo apt-get update && sudo apt-get install cbm git-lfs ffmpeg
   

2. Clone the Repository

   git clone https://huggingface.co/svjack/Miuna_Shiodome_wan_2_1_1_3_B_text2video_lora
   cd Miuna_Shiodome_wan_2_1_1_3_B_text2video_lora
   

3. Install Python Dependencies

   pip install torch torchvision
   pip install -r requirements.txt
   pip install ascii-magic matplotlib tensorboard huggingface_hub datasets
   pip install moviepy==1.0.3
   pip install sageattention==1.0.6
   

4. Download Model Weights

   wget https://huggingface.co/Wan-AI/Wan2.1-T2V-14B/resolve/main/models_t5_umt5-xxl-enc-bf16.pth
   wget https://huggingface.co/DeepBeepMeep/Wan2.1/resolve/main/models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth
   wget https://huggingface.co/Wan-AI/Wan2.1-T2V-14B/resolve/main/Wan2.1_VAE.pth
   wget https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_t2v_1.3B_bf16.safetensors
   wget https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_t2v_14B_bf16.safetensors
   

Usage

To generate a video, use the wan_generate_video.py script with the appropriate parameters. Below are examples of how to generate videos using the Miuna_Shiodome model.

Burger

python wan_generate_video.py --fp8 --task t2v-1.3B --video_size 480 832 --video_length 81 --infer_steps 50 \
--save_path save --output_type both \
--dit wan2.1_t2v_1.3B_bf16.safetensors --vae Wan2.1_VAE.pth \
--t5 models_t5_umt5-xxl-enc-bf16.pth \
--attn_mode torch \
--lora_weight Miuna_Shiodome_outputs/Miuna_Shiodome_w1_3_lora-000017.safetensors \
--lora_multiplier 1.0 \
--prompt "In the style of Nagi no Asukara , The video opens with a close-up of a young girl with short dark hair, wearing a light blue jacket over a pink shirt. She is holding a freshly made burger in her hands."

Rose

python wan_generate_video.py --fp8 --task t2v-1.3B --video_size 480 832 --video_length 81 --infer_steps 50 \
--save_path save --output_type both \
--dit wan2.1_t2v_1.3B_bf16.safetensors --vae Wan2.1_VAE.pth \
--t5 models_t5_umt5-xxl-enc-bf16.pth \
--attn_mode torch \
--lora_weight Miuna_Shiodome_outputs/Miuna_Shiodome_w1_3_lora-000017.safetensors \
--lora_multiplier 1.0 \
--prompt "In the style of Nagi no Asukara , The video opens with a close-up of a young girl with short dark hair, wearing a light blue jacket over a pink shirt. She reached for a bouquet of roses. Her hand gently grasped the stems, the motion elegant and deliberate."

School

python wan_generate_video.py --fp8 --task t2v-1.3B --video_size 480 832 --video_length 81 --infer_steps 50 \
--save_path save --output_type both \
--dit wan2.1_t2v_1.3B_bf16.safetensors --vae Wan2.1_VAE.pth \
--t5 models_t5_umt5-xxl-enc-bf16.pth \
--attn_mode torch \
--lora_weight Miuna_Shiodome_outputs/Miuna_Shiodome_w1_3_lora-000017.safetensors \
--lora_multiplier 1.0 \
--prompt "In the style of Nagi no Asukara , The video opens with a close-up of a young girl with short dark hair, wearing a light blue jacket over a pink shirt. She strolls in the campus. The gentle breeze brushes against her face, making her hair sway softly. Her footsteps are light and slow, as if she is savoring every moment of this campus tour. The sun shines through the leaves, creating dappled patterns on the ground. Around her, students are chatting and laughing, some are hurrying to their next classes, while others are enjoying the pleasant outdoor atmosphere just like her."

Parameters

• --fp8: Enable FP8 precision (optional).
• --task: Specify the task (e.g., t2v-1.3B).
• --video_size: Set the resolution of the generated video (e.g., 1024 1024).
• --video_length: Define the length of the video in frames.
• --infer_steps: Number of inference steps.
• --save_path: Directory to save the generated video.
• --output_type: Output type (e.g., both for video and frames).
• --dit: Path to the diffusion model weights.
• --vae: Path to the VAE model weights.
• --t5: Path to the T5 model weights.
• --attn_mode: Attention mode (e.g., torch).
• --lora_weight: Path to the LoRA weights.
• --lora_multiplier: Multiplier for LoRA weights.
• --prompt: Textual prompt for video generation.

Output

The generated video and frames will be saved in the specified save_path directory.

Troubleshooting

• Ensure all dependencies are correctly installed. • Verify that the model weights are downloaded and placed in the correct locations. • Check for any missing Python packages and install them using pip.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Acknowledgments

• Hugging Face for hosting the model weights. • Wan-AI for providing the pre-trained models. • DeepBeepMeep for contributing to the model weights.

Contact

For any questions or issues, please open an issue on the repository or contact the maintainer.

---