LayoutLLM-T2I
Code for ACM MM'23 paper: LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation
파일 탐색기
최종 버전 다운로드 (.zip)- framework.png
- args.txt
- five_category.json
- mix_relation.json
- only_numeral.json
- sampled_non_relation.json
- sampled_only_semantic.json
- sampled_only_spatial.json
- profiles_settings.xml
- Project_Default.xml
- .gitignore
- GLIGEN.iml
- misc.xml
- modules.xml
- vcs.xml
- ade_sem.yaml
- cc3m_canny.yaml
- cc3m_depth.yaml
- cc3m_hed.yaml
- coco2014.yaml
- diode_normal.yaml
- flickr_text.yaml
- flickr_text_image.yaml
- GoldG+SBU+CC3M+O365_box_text.yaml
- GoldG+SBU+CC3M+O365_box_text_image.yaml
- gatedSA_first_conv.jpeg
- README.MD
- __init__.cpython-38.pyc
- base_dataset.cpython-38.pyc
- base_dataset_kp.cpython-38.pyc
- catalog.cpython-38.pyc
- concat_dataset.cpython-38.pyc
- dataset_kp.cpython-38.pyc
- dataset_layout.cpython-38.pyc
- __init__.py
- base_dataset.py
- base_dataset_kp.py
- catalog.py
- concat_dataset.py
- dataset_canny.py
- dataset_depth.py
- dataset_hed.py
- dataset_kp.py
- dataset_layout.py
- dataset_normal.py
- dataset_sem.py
- tsv.py
- tsv_dataset.py
- utils.py
- __init__.py
- base.py
- imagenet.py
- imagenet_clsidx_to_label.txt
- imagenet_train_hr_indices.p
- imagenet_val_hr_indices.p
- index_synset.yaml
- lsun.py
- __init__.py
- model.py
- openaimodel.py
- positionnet.py
- positionnet_with_image.py
- util.py
- __init__.py
- distributions.py
- __init__.py
- modules.py
- modules_backup.py
- __init__.py
- bsrgan.py
- bsrgan_light.py
- utils_image.py
- __init__.py
- contperceptual.py
- vqperceptual.py
- attention.py
- ema.py
- x_transformer.py
- __init__.py
- lr_scheduler.py
- util.py
- __init__.py
- create_meta.py
- distributed.py
- evaluator.py
- image_projection_matrix
- projection_matrix
- task_grounded_generation.py
- trainer.py
- arg_corgis.jpeg
- blank.png
- flower_beach.jpg
- red_bird.jpg
- style_cloudpurple.png
- style_gold.png
- teddy.jpg
- .gitignore
- __init__.py
- app.py
- DejaVuSansMono.ttf
- environment.yaml
- environment_cpu_mps.yaml
- README.md
- Dockerfile
- teaser_v4.png
- __init__.cpython-38.pyc
- keypoint_grounding_tokinzer_input.cpython-38.pyc
- text_grounding_tokinzer_input.cpython-38.pyc
- text_image_grounding_tokinzer_input.cpython-38.pyc
- text_layout_tokinzer_input.cpython-38.pyc
- __init__.py
- canny_grounding_downsampler_input.py
- canny_grounding_tokinzer_input.py
- depth_grounding_downsampler_input.py
- depth_grounding_tokinzer_input.py
- hed_grounding_downsampler_input.py
- hed_grounding_tokinzer_input.py
- keypoint_grounding_tokinzer_input.py
- normal_grounding_downsampler_input.py
- normal_grounding_tokinzer_input.py
- sem_grounding_downsampler_input.py
- sem_grounding_tokinzer_input.py
- text_grounding_tokinzer_input.py
- text_image_grounding_tokinzer_input.py
- text_layout_tokinzer_input.py
- beach.jpg
- bigben.jpg
- canny_robot.png
- clock.png
- dalle2_museum.jpg
- depth_bird.png
- hed_man_eat.png
- normal_tree_building.jpg
- placeholder.png
- readme.txt
- sem_ade_living_room.png
- style_golden.jpg
- util.cpython-38.pyc
- __init__.py
- base.py
- imagenet.py
- imagenet_clsidx_to_label.txt
- imagenet_train_hr_indices.p
- imagenet_val_hr_indices.p
- index_synset.yaml
- lsun.py
- autoencoder.cpython-38.pyc
- __init__.cpython-38.pyc
- ddim.cpython-38.pyc
- ddpm.cpython-38.pyc
- ldm.cpython-38.pyc
- plms.cpython-38.pyc
- __init__.py
- classifier.py
- ddim.py
- ddpm.py
- ldm.py
- plms.py
- autoencoder.py
- attention.cpython-38.pyc
- attention_0419.cpython-38.pyc
- x_transformer.cpython-38.pyc
- __init__.cpython-38.pyc
- gligen_combine_layout.cpython-38.pyc
- keypoint_grounding_net.cpython-38.pyc
- model.cpython-38.pyc
- openaimodel.cpython-38.pyc
- text_grounding_net.cpython-38.pyc
- util.cpython-38.pyc
- __init__.py
- canny_grounding_downsampler.py
- canny_grounding_net.py
- convnext.py
- depth_grounding_downsampler.py
- depth_grounding_net.py
- gligen_combine_layout.py
- grounding_net_example.py
- hed_grounding_downsampler.py
- hed_grounding_net.py
- keypoint_grounding_net.py
- model.py
- normal_grounding_downsampler.py
- normal_grounding_net.py
- openaimodel.py
- openaimodel_original.py
- pseudo_example.py
- resnet.py
- sem_grounding_downsampler.py
- sem_grounding_net.py
- text_grounding_net.py
- text_image_grounding_net.py
- util.py
- __init__.cpython-38.pyc
- distributions.cpython-38.pyc
- __init__.py
- distributions.py
- __init__.cpython-38.pyc
- modules.cpython-38.pyc
- __init__.py
- modules.py
- modules_backup.py
- __init__.py
- bsrgan.py
- bsrgan_light.py
- utils_image.py
- __init__.py
- contperceptual.py
- vqperceptual.py
- attention.py
- attention_original.py
- ema.py
- x_transformer.py
- lr_scheduler.py
- util.py
- clip_score.py
- color150.mat
- convert_ckpt.py
- distributed.py
- gligen_inference.py
- inpaint_mask_func.py
- interface.py
- LICENSE
- main.py
- projection_matrix
- README.md
- SD_input_conv_weight_bias.pth
- trainer.py
- trainer_combined_layout.py
- tsv_split_merge.py
- llm.py
- policy.py
- aesthetic.py
- metrics.py
- base_prompt.py
- data.py
- README.md
- requirements.txt
- train_rl.py
- txt2img.py
- utils.py
# 설치 가이드
1. 코드 내려받기
git clone https://github.com/LayoutLLM-T2I/LayoutLLM-T2I
깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.
cd LayoutLLM-T2I
방금 내려받은 프로젝트 폴더 안으로 이동합니다.
2. Docker
쉬움 추천사전 준비물
- Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
- Docker Desktop 컨테이너를 빌드하고 실행하려면 필요합니다. 설치 후 실행해서 백그라운드에 켜두세요.
⚠️ 이 프로젝트는 규모가 큰 저장소라, 이 방법이 실제 핵심 제품이 아니라 내부 하위 패키지를 가리키는 것일 수 있습니다. README 전체를 함께 확인해보세요.
docker build -f GLIGEN/env_docker/Dockerfile -t layoutllm-t2i .
Dockerfile을 기반으로 실행 가능한 이미지를 빌드합니다.
docker run -p 8080:80 layoutllm-t2i
빌드된 이미지를 실제 컨테이너로 실행합니다.
터미널에 docker compose ps 를 입력해 컨테이너들이 Up 상태인지 확인하세요. README에 포트 번호가 적혀있다면 브라우저에서 http://localhost:포트번호 로 접속해보세요.
// repository documentation
Was this content helpful?
(0 ratings)
