CivArchive
    Basic SDXL Image Generation Workflow for Advanced Users - v1.0
    NSFW
    Preview 17033635
    Preview 17034009
    Preview 17033977
    Preview 17044498
    Preview 17033840
    Preview 17044769
    Preview 17033855
    Preview 17044712
    Preview 17033969
    Preview 17033974
    Preview 17033992
    Preview 17033703
    Preview 17033807
    Preview 17033707
    Preview 17034005
    Preview 17033968
    Preview 17033785
    Preview 17033815
    Preview 17033953

    Militant Hitchhiker's SDXL ImageGen Workflow Datasheet

    1. SDXL Base Model with Optional Refiner:

    - Uses SDXL for image generation

    - Refiner step can be disabled by setting to 1

    2. Multiple LoRA Model Loaders (10):

    - Supports loading up to 10 LoRA models

    - Allows customization of generation process

    3. Integrated Random Prompt Generator:

    - Combines prompt text dictionaries

    - Customizable seed for reproducibility

    Note: The text dictionary inputs need to be placed in ComfyUI/Input/Dictionaries. The format can be customised using your own choice of delimiters, an example is provided in dictionary.txt file.

    4. Advanced Sampling Process:

    - Pre-sampler and latent noise upscale/downscale create a noise map

    - Improves image fidelity

    - Main sampler uses this for final image generation

    5. Ultimate SD Upscale:

    - Performs guided high resolution upscaling on generated images

    6. Image Processing Nodes:

    - FreeU_V2 for improved image quality

    - Self-Attention Guidance for better coherence

    - Kohya Deep Shrink for latent space manipulation

    - HighRes-Fix Script for improved detail

    - CR Upscale Image (FocusFix) for focused detail enhancement

    7. Split CLIP Positive Prompting:

    - First prompt box applies to both CLIP encoders if the second is blank

    8. Utility Nodes:

    - Text Find and Replace: For prompt manipulation (related to style loaders)

    - Math Expression: For dynamic calculations

    - Fast Bypasser: Controls node activation

    - TextAppender: Combines text strings

    - Preview Chooser: Selects and previews generated images

    - SDPromptSaver: Saves images with metadata

    - AnyBus nodes: For flexible data routing

    Note: The Text Find and Replace nodes are related to the style loaders. The expected style format is provided in the example styles.csv file, which needs to be placed in the custom_nodes/was-node-suite directory.

    Upscaler Models:

    1. Image Upscaler Model:

    - ESRGAN\4x_NMKD-Siax_200k.pth

    2. Noise Upscaler Model (4x Only):

    - ESRGAN\4x_Nickelback_70000G.pth

    3. HighRes-Fix Upscaler:

    - ESRGAN\1x-ITF-SkinDiffDetail-Lite-v1.pth

    4. FocusFix Upscaler:

    - ESRGAN\1x-ReFocus-Cleanly.pth

    Custom Nodes:

    Description

    FAQ

    Workflows
    SDXL 1.0

    Looks like we don't have an active mirror for this one right now.

    This archive is kept alive by community contributions, so there are still some gaps, especially for newly removed content.

    Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.

    Details

    Downloads
    346
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    4/24/2025
    Updated
    5/6/2025
    Deleted
    4/24/2025

    Files

    basicSDXLImageGeneration_v10.zip

    Mirrors