sygil-webui/configs/webui/webui_streamlit.yaml

# This file is part of sygil-webui (https://github.com/Sygil-Dev/sygil-webui/).

# Copyright 2022 Sygil-Dev team.
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.

# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU Affero General Public License for more details.

# You should have received a copy of the GNU Affero General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.

# UI defaults configuration file. It is automatically loaded if located at configs/webui/webui_streamlit.yaml.
# Any changes made here will be available automatically on the web app without having to stop it.
# You may add overrides in a file named "userconfig_streamlit.yaml" in this folder, which can contain any subset
# of the properties below.
general:
    version: 1.24.6
    streamlit_telemetry: False
    default_theme: dark
    huggingface_token: ''
    gpu: 0
    outdir: outputs
    default_model: "Stable Diffusion v1.5"
    default_model_config: "configs/stable-diffusion/v1-inference.yaml"
    default_model_path: "models/ldm/stable-diffusion-v1/Stable Diffusion v1.5.ckpt"
    use_sd_concepts_library: True
    sd_concepts_library_folder: "models/custom/sd-concepts-library"
    GFPGAN_dir: "./models/gfpgan"
    GFPGAN_model: "GFPGANv1.4"
    LDSR_dir: "./models/ldsr"
    LDSR_model: "model"
    RealESRGAN_dir: "./models/realesrgan"
    RealESRGAN_model: "RealESRGAN_x4plus"
    upscaling_method: "RealESRGAN"
    outdir_txt2img: outputs/txt2img
    outdir_img2img: outputs/img2img
    outdir_img2txt: outputs/img2txt
    gfpgan_cpu: False
    esrgan_cpu: False
    extra_models_cpu: False
    extra_models_gpu: False
    gfpgan_gpu: 0
    esrgan_gpu: 0
    keep_all_models_loaded: False
    save_metadata: True
    save_format: "png"
    skip_grid: False
    skip_save: False
    grid_quality: 95
    n_rows: -1
    no_verify_input: False
    no_half: False
    use_float16: False
    precision: "autocast"
    optimized: False
    optimized_turbo: False
    optimized_config: "optimizedSD/v1-inference.yaml"
    enable_attention_slicing: False
    enable_minimal_memory_usage: False
    update_preview: True
    update_preview_frequency: 10

debug:
    enable_hydralit: False

txt2img:
    prompt:
    width:
        value:      512
        min_value:  64
        max_value:  2048
        step:       64

    height:
        value:      512
        min_value:  64
        max_value:  2048
        step:       64

    cfg_scale:
        value:      7.5
        min_value:  1.0
        step:       0.5

    seed: ""
    batch_count:
        value:      1

    batch_size:
        value:      1

    sampling_steps:
        value:      30
        min_value:  10
        max_value:  250
        step:       10

    LDSR_config:
        sampling_steps: 50
        preDownScale: 1
        postDownScale: 1
        downsample_method: "Lanczos"

    default_sampler: "k_euler"
    separate_prompts: False
    update_preview: True
    update_preview_frequency: 10
    normalize_prompt_weights: True
    save_individual_images: True
    save_grid: True
    group_by_prompt: False
    save_as_jpg: False
    use_GFPGAN: False
    use_RealESRGAN: False
    use_LDSR: False
    RealESRGAN_model: "RealESRGAN_x4plus"
    use_upscaling: False

    variant_amount:
        value:      0.0
        min_value:  0.0
        max_value:  1.0
        step:       0.01

    variant_seed: ""
    write_info_files: True

txt2vid:
    default_model: "runwayml/stable-diffusion-v1-5"
    custom_models_list: ["runwayml/stable-diffusion-v1-5", "CompVis/stable-diffusion-v1-4", "hakurei/waifu-diffusion"]
    prompt:
    width:
        value:      512
        min_value:  64
        max_value:  2048
        step:       64

    height:
        value:      512
        min_value:  64
        max_value:  2048
        step:       64

    cfg_scale:
        value:      7.5
        min_value:  1.0
        step:       0.5

    batch_count:
        value:      1

    batch_size:
        value:      1

    sampling_steps:
        value:      30
        min_value:  10
        max_value:  250
        step:       10

    num_inference_steps:
        value:      200
        min_value:  10
        max_value:  500
        step:       10

    seed: ""
    default_sampler: "k_euler"
    scheduler_name: "klms"
    separate_prompts: False
    update_preview: True
    update_preview_frequency: 10
    dynamic_preview_frequency: True
    normalize_prompt_weights: True
    save_individual_images: True
    save_video: True
    save_video_on_stop: False
    group_by_prompt: True
    write_info_files: True
    do_loop: False
    use_lerp_for_text: False
    save_as_jpg: False
    use_GFPGAN: False
    use_RealESRGAN: False
    RealESRGAN_model: "RealESRGAN_x4plus"
    use_upscaling: False
    variant_amount:
        value:      0.0
        min_value:  0.0
        max_value:  1.0
        step:       0.01

    variant_seed: ""

    beta_start:
        value:      0.00085
        min_value:  0.00010
        max_value:  0.03000
        step:       0.00010
        format:     "%.5f"

    beta_end:
        value:      0.01200
        min_value:  0.00010
        max_value:  0.03000
        step:       0.00010
        format:     "%.5f"

    beta_scheduler_type: "scaled_linear"
    max_duration_in_seconds: 30

    LDSR_config:
        sampling_steps: 50
        preDownScale: 1
        postDownScale: 1
        downsample_method: "Lanczos"

img2img:
    prompt:
    sampler_name: "k_euler"
    denoising_strength:
        value:      0.75
        min_value:  0.0
        max_value:  1.0
        step:       0.01
    # 0: Keep masked area
    # 1: Regenerate only masked area
    mask_mode: 0
    mask_restore: False
    # 0: Just resize
    # 1: Crop and resize
    # 2: Resize and fill
    resize_mode: 0
    # Leave blank for random seed:
    seed: ""
    ddim_eta: 0.0
    width:
        value:      512
        min_value:  64
        max_value:  2048
        step:       64

    height:
        value:      512
        min_value:  64
        max_value:  2048
        step:       64

    cfg_scale:
        value:      7.5
        min_value:  1.0
        step:       0.5

    batch_count:
        value:      1

    batch_size:
        value:      1

    sampling_steps:
        value:      30
        min_value:  10
        max_value:  250
        step:       10

    num_inference_steps:
        value:      200
        min_value:  10
        max_value:  500
        step:       10

    find_noise_steps:
        value:      100
        min_value:  100
        step:       100

    LDSR_config:
        sampling_steps: 50
        preDownScale: 1
        postDownScale: 1
        downsample_method: "Lanczos"

    loopback: True
    random_seed_loopback: True
    separate_prompts: False
    update_preview: True
    update_preview_frequency: 10
    normalize_prompt_weights: True
    save_individual_images: True
    save_grid: True
    group_by_prompt: False
    save_as_jpg: False
    use_GFPGAN: False
    use_RealESRGAN: False
    RealESRGAN_model: "RealESRGAN_x4plus"
    use_upscaling: False
    variant_amount: 0.0
    variant_seed: ""
    write_info_files: True

img2txt:
    batch_size: 2000
    blip_image_eval_size: 512
    keep_all_models_loaded: False

concepts_library:
    concepts_per_page: 12

gfpgan:
  strength: 100

textual_inversion:
    pretrained_model_name_or_path: "models/diffusers/stable-diffusion-v1-4"
    tokenizer_name: "models/clip-vit-large-patch14"


daisi_app:
    running_on_daisi_io: False

model_manager:
    models:
        stable_diffusion:
            model_name:     "Stable Diffusion v1.5"
            save_location:  "./models/ldm/stable-diffusion-v1"
            files:
                model_ckpt:
                    file_name:  "Stable Diffusion v1.5.ckpt"
                    download_link:  "https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt"

        gfpgan:
            model_name:     "GFPGAN"
            save_location:  "./models/gfpgan"
            files:
                gfpgan_1_4:
                    file_name:  "GFPGANv1.4.pth"
                    download_link:  "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/GFPGANv1.4.pth"
                resnet_50:
                    file_name: "detection_Resnet50_Final.pth"
                    save_location:  "./gfpgan/weights"
                    download_link: "https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth"
                parsing_parsenet:
                    file_name: "parsing_parsenet.pth"
                    save_location:  "./gfpgan/weights"
                    download_link: "https://github.com/xinntao/facexlib/releases/download/v0.2.2/parsing_parsenet.pth"


        realesrgan:
            model_name:     "RealESRGAN"
            save_location:  "./models/realesrgan"
            files:
                x4plus:
                    file_name: "RealESRGAN_x4plus.pth"
                    download_link:  "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth"
                x4plus_anime_6b:
                    file_name: "RealESRGAN_x4plus_anime_6B.pth"
                    download_link:  "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth"


        waifu_diffusion:
            model_name:     "Waifu Diffusion v1.3"
            save_location:  "./models/custom"
            files:
                waifu_diffusion:
                    file_name: "Waifu-Diffusion-v1-3 Full ema.ckpt"
                    download_link:  "https://huggingface.co/hakurei/waifu-diffusion-v1-3/resolve/main/wd-v1-3-full.ckpt"


        trinart_stable_diffusion:
            model_name:     "TrinArt Stable Diffusion v2"
            save_location:  "./models/custom"
            files:
                trinart:
                    file_name: "trinart.ckpt"
                    download_link:  "https://huggingface.co/naclbit/trinart_stable_diffusion_v2/resolve/main/trinart2_step95000.ckpt"
                    
        sd_wd_ld_trinart_merged:
            model_name:     "SD1.5-WD1.3-LD-Trinart-Merged"
            save_location:  "./models/custom"
            files:
                sd_wd_ld_trinart_merged:
                    file_name: "SD1.5-WD1.3-LD-Trinart-Merged.ckpt"
                    download_link:  "https://huggingface.co/ZeroCool94/sd1.5-wd1.3-ld-trinart-merged/resolve/main/SD1.5-WD1.3-LD-Trinart-Merged.ckpt"

        stable_diffusion_concept_library:
            model_name:     "Stable Diffusion Concept Library"
            save_location:  "./models/custom/sd-concepts-library/"
            files:
                concept_library:
                    file_name: ""
                    download_link:  "https://github.com/Sygil-Dev/sd-concepts-library"

        blip_model:
            model_name:     "Blip Model"
            save_location:  "./models/blip"
            files:
                blip:
                    file_name: "model__base_caption.pth"
                    download_link:  "https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model*_base_caption.pth"

        ldsr:
            model_name: "Latent Diffusion Super Resolution (LDSR)"
            save_location:  "./models/ldsr"
            files:
                project_yaml:
                    file_name:     "project.yaml"
                    download_link:  "https://heibox.uni-heidelberg.de/f/31a76b13ea27482981b4/?dl=1"

                ldsr_model:
                    file_name:     "model.ckpt"
                    download_link:  "https://heibox.uni-heidelberg.de/f/578df07c8fc04ffbadf3/?dl=1"