AIO Loaders have been removed as of v12. If you use AIO models, you can easily add a checkpoint loader to replace the existing loaders and connect them accordingly.
The default Load Diffusion Model loader looks for your Krea 2 Turbo model in the models/diffusion_models folder.
This workflow has the following functions/features:
Text to Image
Multiple Lora Loading
Wildcards
Upscale
Detailers (removed on v12)
Save Image with full resource metadata in CivitAI readable format
These will work with Anima Turbo models, but you'll have to figure out the settings.
Support Policy
These workflows are provided as-is and without guaranteed support.
I do not provide support for third-party applications, modified versions, redistributed copies, reposts, bundles, or installations obtained from unofficial sources.
Inclusion of these workflows in another project does not imply my endorsement, involvement, or responsibility for that project.
Disclaimer
Responsibility for generated content falls on the user of these workflows. I do not control how people prompt or what they use.
Downloading/installation of ComfyUI and/or any related custom nodes for these workflows are at the installer's own risk.
Description
Krea 2 Turbo Workflow — v4 Release Notes
This update reorganizes the workflow, adds optional prompt rewriting and attention controls, and revises the default generation and upscale settings.
New additions
Added an optional Qwen Prompt Reformat section to rewrite prompts into natural-language descriptions. Includes instructions to preserve the supplied details, text cleanup, and an output preview. Bypassed by default. Credit goes to @bkidderz for this. Note: the output sometimes breaks on this, but overall it is pretty reliable. This is very similar to using Prompt Enhancer. It will add about 20 seconds to your generation time depending on your hardware.
Added the BK Wildcards Selector as an additional prompt-building tool. The selector is currently bypassed and unconnected; its output can be connected into one of the positive prompt text boxes.
Added an optional Model Attention Backend node with Comfy Kitchen Attention selected. Comfy Kitchen is natively part of ComfyUI and does not require you to install anything new unless your Comfy install is very old. Bypassed by default.
Added accompanying notes and updated the custom-node list.
Workflow changes
Reorganized groups and bypass controls for model loading, wildcards, upscaling, detailers, and image saving.
Removed the separate Upscale with Model branch. Basic Lanczos resizing, SeedVR2, and Ultimate SD Upscale remain available.
Enabled SeedVR2 in the saved workflow and changed its denoise setting from 0.40 to 0.70.
Changed LoRA routing so the Power LoRA Loader patches the diffusion model while text encoding uses the loaded text encoder directly.
Replaced zeroed positive conditioning with a separate, empty negative-prompt encoder.
Custom latent dimensions can now be entered directly without the resolution calculator overriding them by default.
Updated several explanatory notes throughout the workflow.
Updated saved defaults
Initial resolution: 832 × 1216 → 768 × 1344.
USDU tile size: 1280 × 1280 → 1536 × 1536.
USDU tile padding: 96 → 128.
Global Seed behavior: increment for each node → randomize for each node.
One optional detailer’s selected detector changed from hands to hair.
The workflow retains 2× basic upscaling, optional detailer passes, color correction, image comparisons, and image saving with metadata. Select your installed models and review the enabled groups before generating.