Kinich_wan_2_1_1_3_B_text2video_lora

Kinich Text-to-Video Generation

This repository contains the necessary steps and scripts to generate anime-style videos using the Kinich text-to-video model with LoRA (Low-Rank Adaptation) weights. The model produces high-quality anime-style videos based on textual prompts with distinctive geometric and neon aesthetic.

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/Kinich_wan_2_1_1_3_B_text2video_lora
   cd Kinich_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/svjack/hakoniwa_anime_wan2_1_models/resolve/main/aniWan2114BFp8E4m3fn_t2v13B.safetensors
   

Usage

To generate a video, use the wan_generate_video.py script with the appropriate parameters. Below are examples demonstrating the Kinich aesthetic:

Futuristic City Scene

• Original Weight

python wan_generate_video.py --fp8 --task t2v-1.3B --video_size 480 832 --video_length 81 --infer_steps 35 \
--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 Kinich_w1_3_outputs/Kinich_w1_3_lora-000070.safetensors \
--lora_multiplier 1.0 \
--prompt "anime style, In the style of Kinich, This is a digital anime-style illustration featuring a young male character with teal and dark blue, tousled hair adorned with geometric, neon-colored patterns. He has large, expressive green eyes and a slight, confident smile. He is wearing a black, form-fitting outfit with gold and teal geometric designs, a matching black glove with similar patterns, and a headband with a similar design. His right hand is raised to his chin. The scene takes place outdoors in a futuristic cityscape at sunset, with glowing skyscrapers, floating platforms, and streams of light forming dynamic trails in the sky."

<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/KyGFDUTsDOzLAB4AizHOi.mp4"></video>

• Anime Weight

python wan_generate_video.py --fp8 --task t2v-1.3B --video_size 480 832 --video_length 81 --infer_steps 35 \
--save_path save --output_type both \
--dit aniWan2114BFp8E4m3fn_t2v13B.safetensors --vae Wan2.1_VAE.pth \
--t5 models_t5_umt5-xxl-enc-bf16.pth \
--attn_mode torch \
--lora_weight Kinich_w1_3_outputs/Kinich_w1_3_lora-000070.safetensors \
--lora_multiplier 1.5 \
--prompt "anime style, In the style of Kinich, This is a digital anime-style illustration featuring a young male character with teal and dark blue, tousled hair adorned with geometric, neon-colored patterns. He has large, expressive green eyes and a slight, confident smile. He is wearing a black, form-fitting outfit with gold and teal geometric designs, a matching black glove with similar patterns, and a headband with a similar design. His right hand is raised to his chin. The scene takes place outdoors in a futuristic cityscape at sunset, with glowing skyscrapers, floating platforms, and streams of light forming dynamic trails in the sky."

<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/iz-dbknAVaBlyyEK-2hGU.mp4"></video>

Action Sequence

python wan_generate_video.py --fp8 --task t2v-1.3B --video_size 480 832 --video_length 81 --infer_steps 35 \
--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 Kinich_w1_3_outputs/Kinich_w1_3_lora-000070.safetensors \
--lora_multiplier 1.0 \
--prompt "anime style, In the style of Kinich, This is a digital anime-style illustration featuring a young male character with teal and dark blue, tousled hair adorned with geometric, neon-colored patterns. He has large, expressive green eyes and a slight, confident smile. He is wearing a black, form-fitting outfit with gold and teal geometric designs. The background depicts a high-energy action sequence set in a partially destroyed urban landscape. Explosions of glowing energy ripple through the air, and fragments of debris float around him as he levitates slightly, surrounded by swirling particles of light."

<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/KXxdm49gfhEdu5aDDg59h.mp4"></video>

Interactive Mode

For experimenting with different prompts:

python wan_generate_video.py --fp8 --task t2v-1.3B --video_size 480 832 --video_length 81 --infer_steps 35 \
--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 Kinich_w1_3_outputs/Kinich_w1_3_lora-000070.safetensors \
--lora_multiplier 1.0 \
--interactive

"anime style, In the style of Kinich ,This is a digital anime-style illustration featuring a young male character with teal and dark blue, tousled hair adorned with geometric, neon-colored patterns. He has large, expressive green eyes and a slight, confident smile. He is wearing a black, form-fitting outfit with gold and teal geometric designs, a matching black glove with similar patterns, and a headband with a similar design. His right hand is raised to his chin. The background is a brightly lit indoor setting with a table covered in gold coins and a signboard with colorful text. The overall color palette is vibrant, with a mix of neon and metallic hues."

<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/iZS8tAczgAOytBW81R4wp.mp4"></video>

Genshin TCG (原神幻影卡牌)

Genshin_TCG ，原神集换式卡牌游戏，动漫风格，模仿基尼奇的风格。基尼奇是一位年轻的男性角色，有着蓝绿色和深蓝色的凌乱头发，头发上点缀着霓虹色的几何图案。他有一双富有表现力的大绿眼睛，脸上挂着自信的微笑。他身穿一件带有金色和蓝绿色几何图案的黑色紧身衣，戴着一只同样图案的黑色手套和一条同样设计的头带。他在森林里面探索时发现森林地面有一个宝箱，他走到宝箱前面，打开宝箱，拿出了里面的红苹果，吃了一口。

<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/ctgZRMFMIqEpyCq2bcH-z.mp4"></video>

Sequential Steps

[1] anime style, In the style of Kinich, Kinich read a book on desk.

[2] anime style, In the style of Kinich, Kinich eat a hamburger.

[3] anime style, In the style of Kinich, Kinich make a call using your mobile phone when standing from the desk.

[4] anime style, In the style of Kinich, Kinich drink a cup of tea on desk.

<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/qi4dFHdsCoOl20CTx90Sw.mp4"></video>

Key Parameters

• --fp8: Enable FP8 precision (recommended)
• --task: Model version (t2v-1.3B)
• --video_size: Output resolution (e.g., 480 832)
• --video_length: Number of frames (typically 81)
• --infer_steps: Quality vs speed trade-off (35-50)
• --lora_weight: Path to Kinich LoRA weights
• --lora_multiplier: Strength of LoRA effect (1.0 recommended)
• --prompt: Should include "In the style of Kinich" for best results

Style Characteristics

For optimal results, prompts should describe:

• Characters with geometric neon hair patterns
• Black outfits with gold/teal designs
• Futuristic or high-energy backgrounds
• Vibrant color palettes with glowing elements
• Dynamic poses and expressions

Output

Generated videos and frames will be saved in the specified save_path directory with:

• MP4 video file
• Individual frames as PNG images

Troubleshooting

• Verify all model weights are correctly downloaded • Ensure sufficient GPU memory (>=12GB recommended) • Check for version conflicts in Python packages

License

This project is licensed under the MIT License.

Acknowledgments

• Hugging Face for model hosting • Wan-AI for base models • svjack for LoRA adaptation

For support, please open an issue in the repository.