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 - v7
This update focuses on prompt handling, wildcard integration, and revised upscale defaults.
Prompt reformatting
Reworked the optional Qwen Prose Reformat setup to use a dedicated, editable system-prompt node, replacing manually assembled chat wrappers.
Expanded the instructions for clothing coverage, layering, footwear, prop handling, and physical relationships.
Added guidance for preserving mixed styles, such as an anime face with realistically rendered hair, body, and clothing.
Added instructions for supplying a suitable background and cinematic lighting when those details are unspecified.
Increased the text-generation limit from 450 to 1,024 tokens and adjusted generation settings.
Added a troubleshooting note for failed reformat attempts.
Wildcard integration
Connected Impact Wildcards and BKWILDCARDS through dedicated switches with empty-text fallbacks.
Both wildcard sources now combine with the main positive prompt before optional reformatting. The combined prompt also feeds generation when reformatting is bypassed.
Added separate text previews for both wildcard sources.
Updated the BKWILDCARDS Selector from 0.9.18 to 0.9.19.
Both wildcard sections remain bypassed by default.
Upscaling and refinement
Revised USDU defaults to Euler + Normal, 3 steps, CFG 1.0, and 0.22 denoise.
Changed USDU tiles from 1536 × 1536 to 1024 × 1024, retaining 128-pixel padding. Tiles are more friendly for folks with non-whale hardware, but a large single tile is generally more stable.
Set USDU to run without the loaded LoRAs by default. The existing switch allows them to be enabled.
Adjusted optional SeedVR2 denoise settings to 1.0 before USDU and 0.15 after USDU.
Changed SeedVR2 tiled VAE encoding and decoding to 1,024-pixel tiles with 64-pixel overlap.
Adjusted the third detailer’s denoise to 0.25 and set its wildcard specification to
eye. You can change to something else or delete the text. When I use this detailer, it is only for eyes.
Other changes
Changed the default portrait resolution to 832 × 1216.
Color correction is now bypassed by default.
Removed the Global Seed node and its group control.
Updated seed-locking instructions, upscale recommendations, and workflow labels.
Setup notes
Update BKWILDCARDS for the revised selector. Wildcards, prompt reformatting, SeedVR2 passes, detailers, and color correction are bypassed in the supplied workflow and can be enabled as needed.