CivArchive
    Model Card - v4 beta1
    NSFW
    Preview 17599246
    Preview 17599305
    Preview 17596182

    CLICK EXPAND AND READ ME PLZ!

    This ComfyUI workflow generates a Model Card for showcasing checkpoints or LoRAs.

    A rewrite of the Model Card workflow by @Stevie2k8

    V4 Beta 2

    V4 Beta 2 is another complete rewrite to reduce memory usage and complexity.

    This version uses Flow Control techniques together with Autoqueue in order to perform different actions separately in a controlled order.

    Intermediary steps produce images that are saved into a project folder.

    This version uses my custom IndustrialMagick node that requires you to install ImageMagick on your machine. This is an opensource command line application similar to photoshop or gimp, which is much more powerful and optimized than image manipulation within comfyUI.


    Looking for feedbacks before adding more features.

    Common issue resolution:

    1. project folder not created

    • I use ComfyUI save node to create the project folder inside your ComfyUI output directory by saving an empty image.

    • The output directory path can be changed by modifying your run_cpu.bat or run_nvidia_gpu.bat start file. (these files only exist on ComfyUI Portable for windows)
      By default, it is located in: `...\ComfyUI_windows_portable\ComfyUI\output`

    • If the creation fails, which it should not, you can create the directory manually.

    2. Error at the grid creation stage

    • You can check the actual image magick error in the logs in the comfyui cmd window before the same message as displayed in the error popup.

    • From my experience debugging the workflow, I believe the error will be because image magick cannot open one of the row_xx.png files listed in the rows.txt list file.

    • In that case, hit 0 or reset the view to go back to the control panel, below from the control flow group, you have a box to provide the absolute path to your comfyUI output directory. Please check that the path is valid.

    • You can also go to the project folder and open the rows.txt file to double check the paths of all row images.

    3. Error at the card creation stage

    • This should not happen, but did happen in debugging and was corrected.

    • If the flow controls is not set properly or if you disable the random number generators, ComfyUI may skip the header or grid generation because their parameters did not change.

    • If this issue presents itself to you, you can disable the autoqueue, set the header and grid controllers to active, set the loopCount to the number of selected rows plus one (27 if you selected all 26 prompt groups) and queue. It will generate the header and grid, then you can set all values as before but also enable the card controller, generation will happen without error this time.

    V4 Beta 2 Flow Control explanation:

    Flow control serves two purposes in V4 beta 2.

    Order of generation

    You will notice a chain from the loop count value all the way to the autoqueue. That's called the signal. This is a technique to enforce that several steps happen before others.

    Workflow routing


    This workflow is designed to queue itself twice before starting to generate row images and once after. Before each queue the loop counter value will update and the workflow will activate or deactivate multiple stages.

    Before I describe the order of operations, let's define some terms:

    • loopCount: is an integer value starting at -1. It keeps track of the current iteration. It acts as an index in a programmatic loop. It's maximum value will be one more than the number of prompt groups you select to generate, so if you select 3 it will be 4.

    • N: represents the number of prompt groups selected. loopCount maximum value will be N+1.

    • Controllers: ComfyUI has a specific order of operations. It will only execute nodes in a branch that ends with a saving or preview node.This allows us to activate or deactivate a route or diagram branch by disabling the saving or preview node at its end. I have put these nodes into separate groups called controllers.

    • In the following flow explanation, I will write [autoqueue] to represent the last action in a workflow. That action is different whether you have activated the autoqueue option in the workflow or not. In the former case, it corresponds to the last node in the workflow queueing itself, in the latter, it corresponds to you the user queueing the workflow at the end of its execution.


    Flow control works as follow:

    Before you queue for the first time, ensure that:

    • all controllers are set to NO (disabled).

    • the value of loopCount is set to -1

    You queue once.

    STEP -1

    The workflow enables two controllers:

    • folder creation

    • rows.txt text file reset

    The workflow updates the value of loopCount to 0.

    [autoqueue]

    STEP 0
    The workflow runs:

    • folder creation

    • rows.txt text file reset

    The workflow disables two controllers:

    • folder creation

    • rows.txt text file reset

    The workflow enables three controllers:

    • row

    • row2

    • save row image name to rows.txt

    The workflow updates the value of loopCount to 1.
    [autoqueue]

    STEP 1 to STEP N-1
    The workflow runs:

    • row

    • row2

    • save row image name to rows.txt

    The workflow updates the value of loopCount by 1.
    [autoqueue]

    STEP N
    The workflow runs:

    • row

    • row2

    • save row image name to rows.txt

    The workflow disables three controllers:

    • row

    • row2

    • save row image name to rows.txt

    The workflow enables three controllers:

    • header

    • grid

    • card

    The workflow updates the value of loopCount to N+1.
    [autoqueue]


    STEP N+1
    The workflow runs:

    • header

    • grid

    • card

    The workflow disables three controllers:

    • header

    • grid

    • card

    The workflow updates the value of loopCount to -1.

    No queue, the workflow executed completely.

    V4 Beta 1

    I am trying to reduce the memory load from V3.
    In V4 I saw significant reduction of the RAM in use after an initial peak.
    Looking for feedbacks before adding more features.

    V3 Status

    Issues:

    • Group Average gen times: check formula

    • Global generation times: not working, issue with lists

    • VRAM hungry

    Description

    This workflow generates a customizable Model Card.

    Header

    • Can be toggled on or off entirely.

    • Logo to the left, toggable.

    • Generation info.

    • Baner to the right, toggable.

    Grid body

    • Customizable number of columns (recommended values: 1 or 2).

    • Toggable prompt groups (26).

    • Customizable max number of images per group (recommended <8).

    • Supports groups of different sizes.

    • Each group prints one headline.

    • Each group may print one description.

    • Each image in group prints a label.

    V3 exclusive

    • Each image may print a generation time, toggable.

    • (broken) Each group may print a total or average generation time.

    • (planned) Total or global average generation time may print to the header.

    Use

    • You may clone this repository into the pysssss-workflows ComfyUI subdirectory.

    • Load the .json file.

    • Install missing nodes using the ComfyUI Manager.

    • (V3) Install my custom node "KSamplerTimer" for Version 3.

      • Install with the ComfyUI Manager: Insall via git URL: https://gitlab.com/lanterieur/comfyui_ksamplertimer

      • Get it from CivitAI: CivitAI

      • Get it from the repository: Gitlab

    • Set checkpoint settings.

    • Set default sd1.5 & sdxl image sizes.

    • Set LoRA settings if needed.

    • Set template (columns).

    • Toggle groups to generate.

    • (V2) Toggle "just the right amount" of "batch"es.

    • (Recommended) Disable generation and dry fire.

    • Queue workflow

    FAQ

    • I cannot find the custom node "workflow/xxx".
      This workflow uses "group nodes" which is a built in feature that groups nodes together. If a group node is red, it's most likely because you are missing a custom node inside the group node. Try installing missing custom nodes from the ComfyUI Manager.
      Alternatively, inspect the missing node errors in the ComfyUI console to find which custom nodes to install.

    Changes

    V 3.0.2

    • Updated Hair prompts

    • Updated Headlines

    • Updated Descriptions

    • Updated Labels

    • Fixed bugs:

      • Mismatched Headlines.

      • Mismatched negative prompts.

      • Mismatched labels.

    V 3.0.1

    • Fixed bugs

    V 3.0.0

    • Complete refactor.

    • Swapped native KSampler for custom KSamplerTimer.

    • Supports batch generation with checkpoints configuration from file.

    • Exposes negative prompts and seeds to user.

    • Generates all images in one sampler run (list not batch). => Always regenerates all images.

    • Adds ability to print generation times.

    • Improved GUI:

      • Toggles are black.

      • Anything Everywhere declarations are gold.

      • Number of column is red.

      • Save location controls moved to top.

      • Custom LoRA controls moved to top.

      • Reorganized variable columns.

    • Fixed bugs

    V 2.0.0

    • Refactor.

    • Swapped multiple custom nodes (maths, simple & multiline strings).

    • Improved GUI:

      • Reorganized nodes in columns by functions.

      • Color coded node groups.

      • Annotations for users.

    • Removed save to jpg.

    Description

    V4 is a rewrite to reduce memory usage.
    V4 Beta 1 is to get opinions.

    As I release V4 Beta 1, I am working on an experimental V4 Beta 2.

    FAQ

    Comments (11)

    IndustrialVectors
    Author
    Jun 28, 2024
    CivitAI

    Feedback on V4 Beta1 wanted!

    sdferfxJul 7, 2024· 1 reaction

    Crashes Brave (and Brave Nightly) on load. Works in Firefox, but sluggish and takes a while for the switchboards/group connection nodes to load. Seems to slow down a lot if I queue all 60-80 prompts at once; much more manageable in batches of 10, but sad because then you have to babysit it. Otherwise really good improvements! Thanks for your work on this.

    IndustrialVectors
    Author
    Jul 8, 2024

    @jeffcookio Hello thank you for the feedback. I am glad to see that I'm already adressing some of your issues with the beta 2.
    I didn't even know it ComfyUI could run in FF. On my machine FF cannot display the node boxes so I've been restricted to Chrome.
    How much RAM does your system have?
    When I first started with V2/V3 boards could take up to a few minutes to load with 16gb of ram. Loading time improved with 32 gb. I didn't notice long loading times with 64gb.
    On V4 beta 2 I am working at reducing the number of nodes to improve loading times, so this will hopefully improve.
    Queuing large number of prompts through ComfyUI GUI is always painful (works better with the API). I have already fixed that in the V4 beta2. Beta 2 uses impact/inspire auto queuers to self manage, I managed to cut the text file middle man and to run by row batches instead of single images, so the next beta won't require so much baby sitting as you call it.

    xidus90Jul 25, 2024

    @IndustrialVectors is will the Beta2 release soon?

    Beta is not working for me (all images are the same and are not added to the grid, they are only in the tmp folder)

    IndustrialVectors
    Author
    Aug 9, 2024

    @xidus90 V4B2 is now out

    EricRollei21Jun 29, 2024· 2 reactions
    CivitAI

    Aha, I finally got V3 to work therefore it makes sense to see a V4! It's cool, thanks. Let me give you my thoughts on v3. While it was nice to have all the gens in one massive model card, I would rather have them higher resolution in files that are more manageable. For myself, I'd rather have individual full resolution files pasted over a white card with the generation text on each one, with model, prompt, sampler, scheduler etc. Next I'd like some way to test a model for which CFG + scheduler + works best. It's kind of strange to go run a model card that takes 20 minutes to complete and not even know if I'm using the best values for generation. Lastly you could use one of the comfy nodes that rates the image to quantify each model set, or even a LLM or Llava to judge how well the model followed the prompt. Haveing quantitative information would be pretty useful - and it could even be broken down by category. For example, the face analysis tools by Matteo / Cubiq can output the age and gender so you could present a number for how accurate the model was. It would be also useful to test for really complex long prompts vs simple ones to see how a model follows. These are just some ideas for you, take them with a grain of salt.

    IndustrialVectors
    Author
    Jun 29, 2024

    Thanks for the comment.

    Correct me if I am wrong, the needs you describe are a testing suite similar to what efficiency nodes and comfy roll provide with their XY implementations.

    In my eyes model cards are not test grids. I'd argue they act as identity cards of sort, to give an overview of a model in a standardized manner. I use model cards to compare models when choosing one that may be best adapted to a task.

    I do run XY grids to determine best generation parameters or use checkpoint creators recommended values for the model cards.

    If you have a use for a standardized model tester, we can discuss such a tool as well.

    EricRollei21Jun 29, 2024

    @IndustrialVectors Maybe so? Your model card already does the sampling, so it could be simple to save out the images with the text overlay in strips for each category (eg age) at full resolution. Yeah maybe the other things like testing CFG and sampler/scheduler is beyond the scope and should be in another tool. Thanks again for the model card tool.

    IndustrialVectors
    Author
    Jun 29, 2024· 1 reaction

    @EricRollei21 In V3 you can probably add a save image node before groups are turned into a grid and get the individual strips.
    But if you really just want the strips, disable the header, only select one group at a time and queue. It should result in each group being exported separately. Make sure to have column count set to 1.

    KotatsuAiDec 23, 2024

    Would you mind sharing your full list of enabled extensions for V3? I simply can't get to open it; after installing an absurd amount of extensions now ComfyUI raises this error with V3:

    Loading aborted due to error reloading workflow data

    TypeError: self2.groupData.oldToNewWidgetMap[n] is undefined

    IndustrialVectors
    Author
    May 10, 2025

    @KotatsuAi I would not mind but the computers I used when working on those model cards are now defunct. I am almost exclusively working with rented servers at the moment. Most automation and complex workflows moved to agentic or programmatic tools and layers.

    Workflows
    Other

    Details

    Downloads
    152
    Platform
    CivitAI
    Platform Status
    Available
    Created
    6/28/2024
    Updated
    5/13/2026
    Deleted
    -

    Files

    modelCard_v4Beta1.zip

    Mirrors

    CivitAI (1 mirrors)