⚠️ Custom Node Disclaimer

This workflow heavily utilizes custom nodes. Manually modifying the ComfyUI file system or improperly managing node installations can break your ComfyUI environment. Ensure you understand how to manage dependencies and custom node directories before altering the underlying installation to prevent conflicts or system instability.
If you are unfamiliar with these topics, please make a backup of your ComfyUI setup before installing new nodes or updating ComfyUI. For beginners, I generally recommend using the portable version, as it is easier to maintain and back up.

May 31 2026 Hotfix:

• Added missing negative prompt and seed to the CivitAI metadata

• Corrected the prefix of the saved file to "Anima"

• Added the node file field to the sub-graph top view

Workflow Overview

This is a structured, production-ready ComfyUI workflow designed exclusively for the Anima (2B-parameter) non-photorealistic text-to-image model. It provides an organized pipeline utilizing color-coded, modular groups to manage the entire generation process from initial input to post-processing. The layout allows for complex routing without requiring manual graph adjustments for each run.

Core Features

• Dual Resolution Modes: Toggle between precise advanced image sizing and straightforward dimension presets using a fast group bypasser.

• Multi-Method Prompting: Choose between standard manual text input or an automated Image-to-Prompt generator that extracts concepts from reference images.

• Turbo Mode Integration: A single-click toggle that loads the Anima Turbo LoRA and overrides base sampling parameters, reducing iteration steps from 30+ to approximately 10. The workflow includes a turbo LoRA fix to avoid unwanted sweat skin.

• Dedicated ControlNet Routing: Independent image inputs for structural guidance (pose, depth, canny) separated from the prompt generation reference.

• Post-Processing Modules: Optional, toggleable groups for Nvidia Video Super Resolution upscaling and basic color correction (brightness, contrast, saturation).

• Stacked LoRA Management: Streamlined application of multiple styling LoRAs via a single Power LoRA Loader.

• Native Metadata Embedding: Automatically writes CivitAI-compatible generation parameters into the final image file.

License

The Anima model is licensed under the CircleStone Labs Non-Commercial License. The model and derivatives are only usable for non-commercial purposes. Additionally, the model constitutes a "Derivative Model" of Cosmos-Predict2-2B-Text2Image, and therefore is subject to the NVIDIA Open Model License Agreement insofar as it applies to Derivative Models.

If you would like a commercial license, please email [email protected]

COMFYUI SECURITY ERROR FIX

If you hit a security level error while trying to install the ComfyUI_NVIDIA_RTX_Nodes custom node from ComfyUI manager:

1. You need to temporarily change the security level in your config.ini file.

• If you are using the portable version, the file is located at:
  ComfyUI/user/__manager/config.ini

• Change the value to:
  security_level = weak

IMPORTANT:
Do NOT forget to restore it back to its original value. It is safe to temporarily lower the security level for this node since it comes directly from the ComfyUI team, but you should restore it afterward for safety reasons.

1. Perform a hard restart of ComfyUI (completely stop it, then start it again).

2. Install the custom node using ComfyUI manager and double-check that it is the official one. The link should point to:
   https://github.com/Comfy-Org/Nvidia_RTX_Nodes_ComfyUI

3. Restart ComfyUI and check if the node works properly.
   If you encounter a dependency error, keep reading...

4. Once everything is working properly, restore your original security level in the config.ini file and restart ComfyUI one final time.

COMFYUI PORTABLE DEPENDENCY ERROR FIX

If you hit a dependency error trying to run the Nvidia VSR node, try this:
Create a backup of your embedded Python directory, in case you break something you can restore your embedded directory later using this backup. Then run the following command:

python -m pip install -U --no-build-isolation nvidia-vfx --index-url https://pypi.nvidia.com

Run the command in your embedded Python directory.
For example: D:\ComfyUI\python_embeded.
This command is designed for CMD. If you're using PowerShell, replace the initial python with .\python.exe.

Detailed instructions are contained in the workflow itself:

• Red nodes are instructions and useful notes.

• Yellow nodes are configurable elements you can adjust to your needs.