EasyAnimate
๐บ An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion
ํ์ผ ํ์๊ธฐ
์ต์ข ๋ฒ์ ๋ค์ด๋ก๋ (.zip)- publish.yml
- 0a3b5fb184936a83.txt
- 1.mp4
- 1.png
- 2.png
- 3.png
- 4.png
- 5.png
- mask.jpg
- Pan_Down.txt
- Pan_Left.txt
- Pan_Right.txt
- Pan_Up.txt
- pose.mp4
- easyanimatev3_workflow_i2v.json
- easyanimatev3_workflow_t2v.json
- easyanimatev4_workflow_i2v.json
- easyanimatev4_workflow_lora.json
- easyanimatev4_workflow_t2v.json
- easyanimatev4_workflow_v2v.json
- easyanimatev5_workflow_i2v.json
- easyanimatev5_workflow_t2v.json
- easyanimatev5_workflow_v2v.json
- easyanimatev5_workflow_v2v_control.json
- easyanimatev5.1_workflow_control_camera.json
- easyanimatev5.1_workflow_control_trajectory.json
- easyanimatev5.1_workflow_i2v.json
- easyanimatev5.1_workflow_t2v.json
- easyanimatev5.1_workflow_v2v.json
- easyanimatev5.1_workflow_v2v_control.json
- comfyui_nodes.py
- README.md
- README_zh-CN.md
- requirements.txt
- utils.py
- easyanimate_video_v1_motion_module.yaml
- easyanimate_video_v2_magvit_motion_module.yaml
- easyanimate_video_v3_slicevae_motion_module.yaml
- easyanimate_video_v4_slicevae_multi_text_encoder.yaml
- easyanimate_video_v5.1_magvit_qwen.yaml
- easyanimate_video_v5_magvit_multi_text_encoder.yaml
- zero_stage2_config.json
- put datasets here.txt
- api.py
- post_infer.py
- bucket_sampler.py
- dataset_image.py
- dataset_image_video.py
- dataset_video.py
- __init__.py
- attention.py
- autoencoder_magvit.py
- embeddings.py
- motion_module.py
- norm.py
- patch.py
- processor.py
- resampler.py
- transformer2d.py
- transformer3d.py
- pipeline_easyanimate.py
- pipeline_easyanimate_control.py
- pipeline_easyanimate_inpaint.py
- pipeline_pixart_magvit.py
- __init__.py
- siglip_v2_5.py
- base_model.py
- clip_model.py
- cross_modeling.py
- README.md
- improved_aesthetic_predictor.py
- reward_fn.py
- ui.py
- __init__.py
- diffusion_utils.py
- discrete_sampler.py
- fp8_optimization.py
- gaussian_diffusion.py
- lora_utils.py
- respace.py
- utils.py
- autoencoder_kl_32x32x4_cogvideox.yaml
- autoencoder_kl_32x32x4_mag.yaml
- autoencoder_kl_32x32x4_mag_v2.yaml
- autoencoder_kl_32x32x4_slice.yaml
- autoencoder_kl_32x32x4_slice_decoder_only.yaml
- autoencoder_kl_32x32x4_slice_t_downsample_8.yaml
- __init__.py
- base.py
- dataset_callback.py
- dataset_image_video.py
- __init__.py
- autoencoder.py
- casual3dcnn.py
- cogvideox_casual3dcnn.py
- cogvideox_enc_dec.py
- enc_dec.py
- omnigen_casual3dcnn.py
- omnigen_enc_dec.py
- __init__.py
- model.py
- util.py
- __init__.py
- distributions.py
- test.png
- __init__.py
- bsrgan.py
- bsrgan_light.py
- utils_image.py
- __init__.py
- contperceptual.py
- vqperceptual.py
- __init__.py
- activations.py
- attention.py
- attention_processors.py
- common.py
- discriminator.py
- down_blocks.py
- downsamplers.py
- gc_block.py
- mid_blocks.py
- up_blocks.py
- upsamplers.py
- ema.py
- lr_scheduler.py
- util.py
- environment.yaml
- LICENSE
- README.md
- README_zh-CN.md
- setup.py
- put preprocess datasets here.txt
- easyocr_detection_patched.py
- vila_siglip_encoder_patched.py
- beautiful_prompt.txt
- rewrite.txt
- stage_1_video_splitting.sh
- stage_2_video_filtering.sh
- stage_3_video_recaptioning.sh
- __init__.py
- bpe_simple_vocab_16e6.txt.gz
- longclip.py
- model_longclip.py
- README.md
- simple_tokenizer.py
- __init__.py
- bpe_simple_vocab_16e6.txt.gz
- README.md
- simple_tokenizer.py
- viclip.py
- viclip_text.py
- viclip_vision.py
- filter.py
- gather_jsonl.py
- get_meta_file.py
- image_evaluator.py
- logger.py
- siglip_v2_5.py
- video_dataset.py
- video_evaluator.py
- video_utils.py
- beautiful_prompt.py
- caption_rewrite.py
- compute_motion_score.py
- compute_semantic_consistency.py
- compute_text_score.py
- compute_video_quality.py
- cutscene_detect.py
- filter_meta_train.py
- internvl2_video_recaptioning.py
- README.md
- README_zh-CN.md
- requirements.txt
- video_splitting.py
- __init__.py
- put models here.txt
- report_v4.md
- report_v4_zh-CN.md
- report_v5.md
- report_v5_1.md
- report_v5_1_zh-CN.md
- report_v5_zh-CN.md
- README_DEMO.md
- README_TRAIN.md
- README_TRAIN_CONTROL.md
- README_TRAIN_LORA.md
- README_TRAIN_REWARD.md
- train.py
- train.sh
- train_control.py
- train_control.sh
- train_lcm_lora.py
- train_lcm_lora.sh
- train_lora.py
- train_lora.sh
- train_reward_lora.py
- train_reward_lora.sh
- train_vae.py
- train_vae.sh
- .gitignore
- __init__.py
- app.py
- Dockerfile.ds
- install.py
- LICENSE
- predict_i2v.py
- predict_t2v.py
- predict_v2v.py
- predict_v2v_control.py
- pyproject.toml
- README.md
- README_ja-JP.md
- README_zh-CN.md
- requirements.txt
# ์ค์น ๊ฐ์ด๋
1. ์ฝ๋ ๋ด๋ ค๋ฐ๊ธฐ
git clone https://github.com/aigc-apps/EasyAnimate
๊นํ๋ธ์์ ํ๋ก์ ํธ ์ฝ๋ ์ ์ฒด๋ฅผ ๋ด ์ปดํจํฐ๋ก ๋ด๋ ค๋ฐ์ต๋๋ค.
cd EasyAnimate
๋ฐฉ๊ธ ๋ด๋ ค๋ฐ์ ํ๋ก์ ํธ ํด๋ ์์ผ๋ก ์ด๋ํฉ๋๋ค.
2. Docker
์ฌ์ ์ถ์ฒ์ฌ์ ์ค๋น๋ฌผ
- Git GitHub์์ ํ๋ก์ ํธ ์ฝ๋๋ฅผ ๋ด๋ ค๋ฐ์ผ๋ ค๋ฉด ํ์ํฉ๋๋ค.
- Docker Desktop ์ปจํ ์ด๋๋ฅผ ๋น๋ํ๊ณ ์คํํ๋ ค๋ฉด ํ์ํฉ๋๋ค. ์ค์น ํ ์คํํด์ ๋ฐฑ๊ทธ๋ผ์ด๋์ ์ผ๋์ธ์.
docker pull mybigpai-public-registry.cn-beijing.cr.aliyuncs.com/easycv/torch_cuda:easyanimate
์ด ๋ช ๋ น์ด๋ฅผ ํฐ๋ฏธ๋์ ๊ทธ๋๋ก ์ ๋ ฅํด ์คํํ์ธ์.
docker run -it -p 7860:7860 --network host --gpus all --security-opt seccomp:unconfined --shm-size 200g mybigpai-public-registry.cn-beijing.cr.aliyuncs.com/easycv/torch_cuda:easyanimate
๋น๋๋ ์ด๋ฏธ์ง๋ฅผ ์ค์ ์ปจํ ์ด๋๋ก ์คํํฉ๋๋ค.
ํฐ๋ฏธ๋์ docker compose ps ๋ฅผ ์
๋ ฅํด ์ปจํ
์ด๋๋ค์ด Up ์ํ์ธ์ง ํ์ธํ์ธ์. README์ ํฌํธ ๋ฒํธ๊ฐ ์ ํ์๋ค๋ฉด ๋ธ๋ผ์ฐ์ ์์ http://localhost:ํฌํธ๋ฒํธ ๋ก ์ ์ํด๋ณด์ธ์.
์ด ๋ ํฌ์ README์ ์ ํ ์ค์ ๋ช ๋ น์ด๋ฅผ ๊ทธ๋๋ก ๊ฐ์ ธ์์ต๋๋ค.
3. Python
์ฌ์์ฌ์ ์ค๋น๋ฌผ
pip install -r comfyui/requirements.txt
requirements.txt ๋ฑ์ ๋ช ์๋ ํ์ด์ฌ ๋ผ์ด๋ธ๋ฌ๋ฆฌ๋ฅผ ์ค์นํฉ๋๋ค.
python app.py
ํ์ด์ฌ ์คํฌ๋ฆฝํธ(๋๋ ๋ชจ๋)๋ฅผ ์คํํฉ๋๋ค.
์๋ฌ ๋ฉ์์ง ์์ด ์คํ๋๊ณ ํฐ๋ฏธ๋์ ์๋ด ๋ฌธ๊ตฌ๊ฐ ์ถ๋ ฅ๋๋ฉด ์ ์์
๋๋ค.
// repository documentation
Was this content helpful?
(0 ratings)