High-end textured portrait - FLUX

comfyui workflow address:Click to go to the workflow page

The advanced high-quality portrait model is trained based on the Flux framework, making the model calls for clip-l, t5xxl_fp8_e4m3fn, and t5xxl_fp16 more intelligent.

Supports both the default workflow and Flux workflow in comfyui

Using the default comfyui workflow increases rendering speed by 12.2% under constant other variables

Usage Instructions

CFG guidance coefficient: 3.5 (adjustable based on situation)

CFG weight: 1

Sampling steps: 30

Sampler: euler

Model Makers Roster

Model training: Ling Chang

Model testing: Feng Du, Xia Dun Duo Chi

Cover design: Axia

Disclaimer:

1.0: The textual content generated by the model service is maintained and used at your discretion. You are responsible for abiding by applicable laws and regulations and the terms of service. Any intellectual property issues arising from the content generated by this service are your responsibility. I am not liable for any losses resulting from this, unless otherwise stated by laws and regulations.

2.0: Without my written authorization, you are not allowed to integrate this model service into any third-party software or service, nor disclose the association between the generated content and this service to any other third party, whether directly or indirectly, explicitly or implicitly.

2.1: Without my written authorization, individuals and organizations are not permitted to use the model for commercial purposes (including but not limited to text rendering, image rendering, face swapping, etc.). You will be liable to compensate the author for any losses caused by your violation of this clause.

3.0: By choosing to use this model, you acknowledge that you have read and agreed to the terms in 1.0, 2.0, and 2.1 above.