This is the start of my 'new' workflow(s). We'll see how long they last before they get nuked by the powers that be.
v1 does not support AIO models by default. (Models with VAE and/or CLIP baked-in).
Your model (not VAE/CLIP) need to be placed in your models/diffusion_models folder to work with the model loader in the v1 workflow.
This workflow has the following functions/features:
Text to Image
Multiple Lora Loading
Global control for Seed
Wildcards
Upscale
Detailers
Color Correction
Save Image with full resource metadata in CivitAI readable format
This workflow is not setup to work with models that use CFG higher than 1.
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.
Installation of ComfyUI and/or any related custom nodes for these workflows are at the installer's own risk.
Description
Added AIO model compatibility
AIO models have the Checkpoint, VAE, and CLIP in a single file.
AIO models need to be placed in your models/checkpoints folder to use this loader.
This loader is in its own group. If both groups are enabled, it will default to the 'normal' loader instead of this one.
USDU
I disconnected the tile_width and tile_height inputs and have set them to 1536 x1536.
Since there is no real guidance on how Krea 2 Turbo behaves with USDU, the settings adjustments were made with the help of ChatGPT after some discussion today.
Adjust the settings to your preference.
Added a new markdown with some ChatGPT recommendations for USDU settings.
Workflow default settings
The first 20 sample images were generated using the default settings on the saved workflow.
Depending on what model and loras you use, these settings will need to be adjusted. Some models just perform bad with USDU no matter what. In those cases, it's better to generate a higher res initial image and either bypass USDU or set the upscale to 1.0 and use USDU as a 2nd pass while setting the tile width and height to match the resolution of the initial image.
FAQ
Comments (2)
Please add controlnet
Sorry, not gonna happen. I have no plans on implementing ControlNet on this workflow.
Other workflows here on CivitAI probably have it implemented on their workflows already. Otherwise, you can try posting a bounty to have someone make a workflow the way you want.