Gladas' Workflow for Anima v3 for Anima

Gladas' Workflow for Anima - v3

NSFW

Moving this up to the top, since it's important:

v1 does not support AIO models by default. (Models with VAE and/or CLIP baked-in). Your Anima/Krea2 models need to be placed in your models/diffusion_models folder to work with the (UNet) loaders in the v1 workflow.

This workflow has the following functions/features:

Text to Image
Image to Image (does not work well IMO)
Multiple Lora Loading
Global control for Seed
Wildcards
Upscale
Separate checkpoint, CLIP, and lora loaders for Upscale+Detailers
Detailers
Color Correction
Save Image with full resource metadata in CivitAI readable format

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

This workflow is not intended to purposefully generate any specific content. Responsibility for generated content falls on the user of the workflow.
Installation of ComfyUI and/or any related custom nodes for these workflows are at the installer's own risk.

Description

Uploaded fixed version of v3. Forgot to connect the CFG to Image Saver.

This version of the workflow is essentially a mirror image of my Krea 2 Turbo v3 workflow, but set for Anima usage.

Added SeedVR2 to the upscale option before USDU

This was used in the first 20 sample images with the denoise ranging from 0.4 to 0.7

The required models for SeedVR2 used in this workflow can be downloaded at:

The VAE model goes into your vae folder and the other model goes into your diffusion_models folder.

If the int8_convrot model is not compatible with your hardware for any reason you can try a different seedvr2 model or just remove the nodes in the SeedVR2 group.

The default settings saved to the workflow are what I used when generating the first 20 sample images with the exception of the denoise setting in the SeedVR2 group ranging from 0.40 to 0.70.