sd-scripts
No description available.
File Explorer
Download Latest Version (.zip)- 01-overview.md
- claude.prompt.md
- Codex.prompt.md
- gemini.prompt.md
- tests.yml
- typos.yml
- dependabot.yml
- FUNDING.yml
- config.json
- merges.txt
- tokenizer.json
- tokenizer_config.json
- vocab.json
- config.json
- spiece.model
- tokenizer.json
- offset_distribution_comparison.png
- offset_distribution_shift3.png
- anima_torch_compile.md
- anima_train_control_net_lllite.md
- anima_train_network.md
- config_README-en.md
- config_README-ja.md
- dataset_metadata.md
- fine_tune.md
- fine_tune_README_ja.md
- flux_train_network.md
- gen_img_README-ja.md
- gen_img_README.md
- hunyuan_image_train_network.md
- inpainting_training.md
- loha_lokr.md
- lumina_train_network.md
- masked_loss_README-ja.md
- masked_loss_README.md
- sd3_train_network.md
- sdxl_train_network.md
- timestep_sampling_offset.md
- train_db_README-ja.md
- train_db_README-zh.md
- train_leco.md
- train_lllite_README-ja.md
- train_lllite_README.md
- train_network.md
- train_network_advanced.md
- train_network_README-ja.md
- train_network_README-zh.md
- train_README-ja.md
- train_README-zh.md
- train_SDXL-en.md
- train_textual_inversion.md
- train_ti_README-ja.md
- validation.md
- wd14_tagger_README-en.md
- wd14_tagger_README-ja.md
- blip.py
- med.py
- med_config.json
- vit.py
- clean_captions_and_tags.py
- hypernetwork_nai.py
- image_loading_dataset.py
- make_captions.py
- make_captions_by_git.py
- merge_captions_to_metadata.py
- merge_dd_tags_to_metadata.py
- prepare_buckets_latents.py
- tag_images_by_wd14_tagger.py
- logo_aihub.png
- __init__.py
- attention.py
- device_prop.py
- diffusers.py
- hijacks.py
- __init__.py
- accelerator_setup.py
- adafactor_fused.py
- anima_models.py
- anima_train_utils.py
- anima_utils.py
- args.py
- attention.py
- attention_processors.py
- caching.py
- checkpoint_io.py
- chroma_models.py
- compile_utils.py
- config_util.py
- controlnet_dataset.py
- custom_offloading_utils.py
- custom_train_functions.py
- dataset.py
- deepspeed_utils.py
- device_utils.py
- dreambooth_dataset.py
- finetuning_dataset.py
- flux_models.py
- flux_train_utils.py
- flux_utils.py
- fp8_optimization_utils.py
- hidden_states.py
- huggingface_util.py
- hunyuan_image_models.py
- hunyuan_image_modules.py
- hunyuan_image_text_encoder.py
- hunyuan_image_utils.py
- hunyuan_image_vae.py
- hypernetwork.py
- jpeg_xl_util.py
- leco_train_util.py
- logging_util.py
- lora_utils.py
- loss.py
- lpw_stable_diffusion.py
- lumina_models.py
- lumina_train_util.py
- lumina_util.py
- mask_generator.py
- model_io.py
- model_util.py
- optimizer.py
- original_unet.py
- qwen_image_autoencoder_kl.py
- qwen_image_autoencoder_kl_2d.py
- safetensors_utils.py
- sai_model_spec.py
- sampling.py
- sd3_models.py
- sd3_train_utils.py
- sd3_utils.py
- sdxl_lpw_stable_diffusion.py
- sdxl_model_util.py
- sdxl_original_control_net.py
- sdxl_original_unet.py
- sdxl_train_util.py
- slicing_vae.py
- strategy_anima.py
- strategy_base.py
- strategy_flux.py
- strategy_hunyuan_image.py
- strategy_lumina.py
- strategy_sd.py
- strategy_sd3.py
- strategy_sdxl.py
- subset.py
- timestep_visualization.py
- train_util.py
- utils.py
- check_lora_weights.py
- control_net_lllite.py
- control_net_lllite_anima.py
- control_net_lllite_for_train.py
- convert_anima_lora_to_comfy.py
- convert_flux_lora.py
- convert_hunyuan_image_lora_to_comfy.py
- dylora.py
- extract_lora_from_dylora.py
- extract_lora_from_models.py
- flux_extract_lora.py
- flux_merge_lora.py
- loha.py
- lokr.py
- lora.py
- lora_anima.py
- lora_diffusers.py
- lora_fa.py
- lora_flux.py
- lora_hunyuan_image.py
- lora_interrogator.py
- lora_lumina.py
- lora_sd3.py
- merge_lora.py
- network_base.py
- oft.py
- oft_flux.py
- resize_lora.py
- sdxl_merge_lora.py
- svd_merge_lora.py
- __init__.py
- model_checkpoint.py
- __init__.py
- test_flux_train_utils.py
- test_leco_train_util.py
- test_lumina_models.py
- test_lumina_train_util.py
- test_lumina_util.py
- test_sai_model_spec.py
- test_strategy_lumina.py
- _verify_inpainting_checkpoint.py
- download_training_data.py
- generate_inpainting_test_data.py
- README.md
- run_sd15_inpainting_test.ps1
- run_sd15_inpainting_test.sh
- run_sdxl_inpainting_test.ps1
- run_sdxl_inpainting_test.sh
- sd15_inpainting_test_ft.toml
- sd15_inpainting_test_lora.toml
- sdxl_inpainting_test_ft.toml
- sdxl_inpainting_test_lora.toml
- test_custom_offloading_utils.py
- test_expand_unet_to_inpainting.py
- test_lumina_train_network.py
- test_mask_generator.py
- test_optimizer.py
- test_qwen_image_autoencoder_kl_2d.py
- test_sdxl_train_leco.py
- test_train_leco.py
- test_validation.py
- manual_test_anima_cache.py
- manual_test_anima_lllite_dryrun.py
- manual_test_anima_real_training.py
- visualize_masks.py
- cache_latents.py
- cache_text_encoder_outputs.py
- canny.py
- convert_diffusers20_original_sd.py
- convert_diffusers_to_flux.py
- detect_face_rotate.py
- latent_upscaler.py
- merge_models.py
- merge_sd3_safetensors.py
- original_control_net.py
- resize_images_to_resolution.py
- show_metadata.py
- .gitignore
- _typos.toml
- anima_minimal_inference.py
- anima_minimal_inference_control_net_lllite.py
- anima_train.py
- anima_train_control_net_lllite.py
- anima_train_network.py
- fine_tune.py
- flux_minimal_inference.py
- flux_train.py
- flux_train_control_net.py
- flux_train_network.py
- gen_img.py
- gen_img_diffusers.py
- hunyuan_image_minimal_inference.py
- hunyuan_image_train_network.py
- inpainting_minimal_inference.py
- LICENSE.md
- lumina_minimal_inference.py
- lumina_train.py
- lumina_train_network.py
- pytest.ini
- README-ja.md
- README.md
- requirements.txt
- sd3_minimal_inference.py
- sd3_train.py
- sd3_train_network.py
- sdxl_gen_img.py
- sdxl_minimal_inference.py
- sdxl_train.py
- sdxl_train_control_net.py
- sdxl_train_control_net_lllite.py
- sdxl_train_leco.py
- sdxl_train_network.py
- sdxl_train_textual_inversion.py
- setup.py
- train_control_net.py
- train_db.py
- train_leco.py
- train_network.py
- train_textual_inversion.py
# Installation Guide
1. Get the code
git clone https://github.com/kohya-ss/sd-scripts
Downloads the entire project code from GitHub to your computer.
cd sd-scripts
Moves into the project folder you just downloaded.
2. Official Install Script
Easy RecommendedPrerequisites
- Python 3 Python is required to use pip.
pip install torch==2.6.0 torchvision==0.21.0 --index-url https://download.pytorch.org/whl/cu124
Installs the package published on PyPI directly β no need to clone the source.
pip install --upgrade -r requirements.txt
Installs the package published on PyPI directly β no need to clone the source.
pip install xformers --index-url https://download.pytorch.org/whl/cu124
Installs the package published on PyPI directly β no need to clone the source.
pip install deepspeed==0.16.7
Installs the package published on PyPI directly β no need to clone the source.
After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.
Pulled directly from this repo's README.
3. Python
EasyPrerequisites
python -m venv venv
Runs the Python script (or module).
pip install torch==2.6.0 torchvision==0.21.0 --index-url https://download.pytorch.org/whl/cu124
Installs the package published on PyPI directly β no need to clone the source.
pip install --upgrade -r requirements.txt
Installs the package published on PyPI directly β no need to clone the source.
pip install xformers --index-url https://download.pytorch.org/whl/cu124
Installs the package published on PyPI directly β no need to clone the source.
pip install deepspeed==0.16.7
Installs the package published on PyPI directly β no need to clone the source.
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)