This model is trained based on the MajicFlux model ecosystem. This model is based on the Chinese style illustration style supplemented by gilded materials. This model needs to be used with the Majicflus model. Using Flux_dve does not work well.
I personally use forge locally to generate images, and you can use it with the Majicflus workflow.
CFG: Default 3.5
The default sampling step is 20, which can be increased to 30 as appropriate.
lora weight: 0.7
When the portrait half-body full-body face screen accounts for a small proportion, it is necessary to open AD to retouch the face and hands.
Trigger word: shanshui,
Prompt word example: A girl stands amidst the mountains and water. Half-body shot.,shanshui
The "MAJICFLUS_麦橘超国风插图" model (hereinafter referred to as "this model") is released and developed by [大佬的鼠DonRat] (hereinafter referred to as "the owner"), based on the FLUX-lora model developed by MajicFlux.
The owner authorizes individuals or organizations to use the images generated by this model for free for non-commercial educational or information dissemination purposes, and:
- Comply with relevant laws and regulations and do not infringe the legitimate rights and interests of this model or any third party.
- When using the image, the image source must be indicated as "generated by [大佬的鼠DonRat]'s "MAJICFLUS_麦橘超国风插图" model".
For commercial use, a commercial license agreement must be signed with the owner first. For commercial licensing and model customization, please contact the owner through the homepage information.
The owner will continue to provide free model updates for individual players to express support and gratitude to community open source contributors. Paid cooperation from commercial users is an important driving force for the development and continuous improvement of this model. Thank you for your understanding and support.
Description
This model is trained based on the MajicFlux model ecosystem. This model is based on the Chinese style illustration style supplemented by gilded materials. This model needs to be used with the Majicflus model. Using Flux_dve does not work well.
I personally use forge locally to generate images, and you can use it with the Majicflus workflow.
CFG: Default 3.5
The default sampling step is 20, which can be increased to 30 as appropriate.
lora weight: 0.7
When the portrait half-body full-body face screen accounts for a small proportion, it is necessary to open AD to retouch the face and hands.
Trigger word: shanshui,
Prompt word example: A girl stands amidst the mountains and water. Half-body shot.,shanshui
The "MAJICFLUS_麦橘超国风插图" model (hereinafter referred to as "this model") is released and developed by [大佬的鼠DonRat] (hereinafter referred to as "the owner"), based on the FLUX-lora model developed by MajicFlux.
The owner authorizes individuals or organizations to use the images generated by this model for free for non-commercial educational or information dissemination purposes, and:
- Comply with relevant laws and regulations and do not infringe the legitimate rights and interests of this model or any third party.
- When using the image, the image source must be indicated as "generated by [大佬的鼠DonRat]'s "MAJICFLUS_麦橘超国风插图" model".
For commercial use, a commercial license agreement must be signed with the owner first. For commercial licensing and model customization, please contact the owner through the homepage information.
The owner will continue to provide free model updates for individual players to express support and gratitude to community open source contributors. Paid cooperation from commercial users is an important driving force for the development and continuous improvement of this model. Thank you for your understanding and support.