Views
No views yet
sudo apt-get update && sudo apt-get install cbm git-lfs ffmpeg1git clone https://huggingface.co/svjack/Xiang_Handsome_wan_2_1_14_B_text2video_lora
2cd Xiang_Handsome_wan_2_1_14_B_text2video_lora 1pip install torch torchvision
2pip install -r requirements.txt
3pip install ascii-magic matplotlib tensorboard huggingface_hub datasets
4pip install moviepy==1.0.3
5pip install sageattention==1.0.61wget https://huggingface.co/Wan-AI/Wan2.1-T2V-14B/resolve/main/models_t5_umt5-xxl-enc-bf16.pth
2wget https://huggingface.co/DeepBeepMeep/Wan2.1/resolve/main/models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth
3wget https://huggingface.co/Wan-AI/Wan2.1-T2V-14B/resolve/main/Wan2.1_VAE.pth
4wget https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_t2v_1.3B_bf16.safetensors
5wget https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_t2v_14B_bf16.safetensorswan_generate_video.py script with the appropriate parameters. Below are examples of how to generate videos using the Xiang_Handsome model.In the style of anime landscape ,一个戴眼镜的年轻的男子赤裸全身站在镜头前，正在吃冰淇凌。夏日清凉： 一个戴着眼镜的清爽青年，身穿简约白色T恤和卡其色短裤，站在阳光斑驳的树荫下，笑容灿烂地品尝着一支缀满巧克力碎的香草冰淇淋。 暖色调，生活感镜头。1人物：
2[年龄] 青年（约18-25岁）[性别] 男性 [服饰特征] 白色T恤和卡其色短裤 [种族/地域特征] 东亚男孩（约一米八身高）
3
4外貌特征：
5• 体型描述：身高约一米八，清爽体型
6• 服饰细节：简约白色T恤和卡其色短裤
7• 配饰：眼镜
8• 其他：具体发型未提及，可假设为普通短发或中长发
9
10状态：
11• 环境：阳光斑驳的树荫下
12• 动作：站立并品尝冰淇淋
13
14表情：
15• 情绪：愉悦、快乐
16• 细节：笑容灿烂
17
18镜头设计：
19
20景别：中景或全身镜头
21角度：正面或侧面拍摄
22焦点：人物和冰淇淋
23运镜：静态镜头或轻微移动
24隐喻：暖色调，生活感镜头
25肢体语言：
26• 手部：一只手拿着冰淇淋，另一只手自然下垂或放在口袋里
27• 躯干：站立姿态，可能稍微前倾以便品尝冰淇淋
28• 整体氛围：轻松愉快的夏日氛围
29
30补充说明：
31• 可加入环境音（例如：鸟鸣声、风声等）
32• 特殊效果建议（例如：突出冰淇淋的细节特写）--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.save_path directory.pip.