Delete Junk

.ipynb_checkpoints/README-checkpoint.md

@@ -1,154 +0,0 @@
-# Prince Star (Kim Hyesung) HunyuanVideo LoRA
-
-This repository contains the necessary setup and scripts to generate videos using the HunyuanVideo model with a LoRA (Low-Rank Adaptation) fine-tuned for Kim Hyesung. Below are the instructions to install dependencies, download models, and run the demo.
-
----
-
-## Installation
-
-### Step 1: Install System Dependencies
-Run the following command to install required system packages:
-```bash
-sudo apt-get update && sudo apt-get install git-lfs ffmpeg cbm
-```
-
-### Step 2: Clone the Repository
-Clone the repository and navigate to the project directory:
-```bash
-git clone https://huggingface.co/svjack/Prince_Star_HunyuanVideo_lora
-cd Prince_Star_HunyuanVideo_lora
-```
-
-### Step 3: Install Python Dependencies
-Install the required Python packages:
-```bash
-conda create -n py310 python=3.10
-conda activate py310
-pip install ipykernel
-python -m ipykernel install --user --name py310 --display-name "py310"
-
-pip install -r requirements.txt
-pip install ascii-magic matplotlib tensorboard huggingface_hub
-pip install moviepy==1.0.3
-pip install sageattention==1.0.6
-
-pip install torch==2.5.0 torchvision
-```
-
----
-
-## Download Models
-
-### Step 1: Download HunyuanVideo Model
-Download the HunyuanVideo model and place it in the `ckpts` directory:
-```bash
-huggingface-cli download tencent/HunyuanVideo --local-dir ./ckpts
-```
-
-### Step 2: Download LLaVA Model
-Download the LLaVA model and preprocess it:
-```bash
-cd ckpts
-huggingface-cli download xtuner/llava-llama-3-8b-v1_1-transformers --local-dir ./llava-llama-3-8b-v1_1-transformers
-wget https://raw.githubusercontent.com/Tencent/HunyuanVideo/refs/heads/main/hyvideo/utils/preprocess_text_encoder_tokenizer_utils.py
-python preprocess_text_encoder_tokenizer_utils.py --input_dir llava-llama-3-8b-v1_1-transformers --output_dir text_encoder
-```
-
-### Step 3: Download CLIP Model
-Download the CLIP model for the text encoder:
-```bash
-huggingface-cli download openai/clip-vit-large-patch14 --local-dir ./text_encoder_2
-```
-
----
-
-## Demo
-
-### Generate Video 1: Kim Hyesung Sun
-Run the following command to generate a video of Prince Kim Hyesung:
-```bash
-python hv_generate_video.py \
-    --fp8 \
-    --video_size 544 960 \
-    --video_length 60 \
-    --infer_steps 30 \
-    --prompt "fantastic artwork of Kim Hyesung. warm sunset in a rural village. the interior of a futuristic spaceship in the background." \
-    --save_path . \
-    --output_type both \
-    --dit ckpts/hunyuan-video-t2v-720p/transformers/mp_rank_00_model_states.pt \
-    --attn_mode sdpa \
-    --vae ckpts/hunyuan-video-t2v-720p/vae/pytorch_model.pt \
-    --vae_chunk_size 32 \
-    --vae_spatial_tile_sample_min_size 128 \
-    --text_encoder1 ckpts/text_encoder \
-    --text_encoder2 ckpts/text_encoder_2 \
-    --seed 1234 \
-    --lora_multiplier 1.0 \
-    --lora_weight Star_im_lora_dir/Star_single_im_lora-000040.safetensors
-```
-
-
-<video controls autoplay src="https://huggingface.co/svjack/Prince_Star_HunyuanVideo_lora/resolve/main/20250204-104122_1234.mp4"></video>
-
-
-### Generate Video 2: Kim Hyesung Sea
-Run the following command to generate a video of Prince Kim Hyesung:
-```bash
-python hv_generate_video.py \
-    --fp8 \
-    --video_size 544 960 \
-    --video_length 60 \
-    --infer_steps 30 \
-    --prompt "surrealist painting of Kim Hyesung. underwater glow, deep sea. a peaceful zen garden with koi pond in the background." \
-    --save_path . \
-    --output_type both \
-    --dit ckpts/hunyuan-video-t2v-720p/transformers/mp_rank_00_model_states.pt \
-    --attn_mode sdpa \
-    --vae ckpts/hunyuan-video-t2v-720p/vae/pytorch_model.pt \
-    --vae_chunk_size 32 \
-    --vae_spatial_tile_sample_min_size 128 \
-    --text_encoder1 ckpts/text_encoder \
-    --text_encoder2 ckpts/text_encoder_2 \
-    --seed 1234 \
-    --lora_multiplier 1.0 \
-    --lora_weight Star_im_lora_dir/Star_single_im_lora-000040.safetensors
-```
-
-
-<video controls autoplay src="https://huggingface.co/svjack/Prince_Star_HunyuanVideo_lora/resolve/main/20250204-111149_1234.mp4"></video>
-
-### Generate Video 1: Kim Hyesung Class
-Run the following command to generate a video of Prince Kim Hyesung:
-```bash
-python hv_generate_video.py \
-    --fp8 \
-    --video_size 544 960 \
-    --video_length 60 \
-    --infer_steps 30 \
-    --prompt "Kim Hyesung, a young person with straight, dark hair, wearing a white school uniform. They are seated in a classroom with other students, all dressed in white uniforms. The background includes a wooden door and blurred figures of other students, suggesting a school setting. The lighting is soft, and the image has a slightly grainy texture, adding to the realistic and candid feel." \
-    --save_path . \
-    --output_type both \
-    --dit ckpts/hunyuan-video-t2v-720p/transformers/mp_rank_00_model_states.pt \
-    --attn_mode sdpa \
-    --vae ckpts/hunyuan-video-t2v-720p/vae/pytorch_model.pt \
-    --vae_chunk_size 32 \
-    --vae_spatial_tile_sample_min_size 128 \
-    --text_encoder1 ckpts/text_encoder \
-    --text_encoder2 ckpts/text_encoder_2 \
-    --seed 1234 \
-    --lora_multiplier 1.0 \
-    --lora_weight Star_im_lora_dir/Star_single_im_lora-000040.safetensors
-```
-
-
-<video controls autoplay src="https://huggingface.co/svjack/Prince_Star_HunyuanVideo_lora/resolve/main/20250204-114357_1234.mp4"></video>
-
-
----
-
-## Notes
-- Ensure you have sufficient GPU resources for video generation.
-- Adjust the `--video_size`, `--video_length`, and `--infer_steps` parameters as needed for different output qualities and lengths.
-- The `--prompt` parameter can be modified to generate videos with different scenes or actions.
-
----