Author: nie norsizu

Workflow source: https://openart.ai/workflows/monkey_well worn_31/realistic photo to manga style/Cl3xyeUX0EVQXY4bVnPN

Resource collection: Talk2AI official website talk2ai.cn
This workflow is designed to transform real-life photos into unique manga styles.
By default, it uses Portrait Master to automatically generate portrait photos, which users can replace with image input nodes.
WD14 reverse keyword generation is applied to the generated portraits, which can be replaced with regular input nodes.
The manga style uses a custom-trained Lora model: Zanshou Kin SDXL Hoko Manga Style, available for download on Civitai (https://civitai.com/models/647408/zanshou kin sdxl hoko manga style).
The base models used are SDXL 1.0 ArienMixXL Asian Portrait and Animagine XL V3.1, both of which can also be downloaded from Civitai.
High-resolution upscaling nodes are not included by default but can be added manually.

[Chinese Translation] Validation Error: The array must contain at most 2 elements in 'nodes[25].pos'
This workflow is designed to convert real-life photos into unique manga-style illustrations.
By default, the workflow uses ComfyUI Portrait Master. Users can easily replace it with image input nodes.
You can replace the WD14 node yourself, which is used for reverse propagation of image keywords.
Custom manga style: Uses a specially trained Lora model: Zanshou Kin SDXL Hoko Manga Style. This model is available for download on Civitai (https://civitai.com/models/647408/zanshou kin sdxl hoko manga style).
Base models: SDXL 1.0 ArienMixXL and Animagine XL V3.1, both accessible on Civitai.
Although not included by default, users can easily integrate high-resolution upscaling nodes.
Version 1.1 Update Notes
Fixed a validation error that occurred when importing workflows into the latest version of ComfyUI. Specific error message: "Validation Error: The array must contain at most 2 elements in 'nodes[25].pos'." The issue has been resolved.