If you like my work, please consider supporting me !

For more information, please visit Patreon!

Overview

FluxesCore-Dev series models are fine-tuned to the Flux.1-Dev models.

Since the original Flux.1 model did not have good Asian facial features, we are training it to have better Asian facial features.

Settings

Please check the "About this version" of this model for details.

NOTE

• Due to the characteristics of Flux.1, it is not a Danbooru tag-based study, so we recommend specifying in English.

• When outputting photorealistic or illustrative styles, the following prefixes are recommended.

e.g.)
・How to outputting photorealistic style [ Photo of a～ ]
Photo of a japanese woman wearing beige sweater and skinny jeans pants.

・How to outputting illustrative style [ Anime of a～ /Anime style of a～]
Anime style of a japanese woman wearing beige sweater and skinny jeans pants.

Disclaimer

• The model creator assumes no liability for any problems or disputes related to the images created using this model.

• This model is not intended for use with adult content. The model creator assumes no liability for any problems that may occur as a result of generating adult-oriented content.

• In the event of any licensing issues, this model may be removed without notice. We appreciate your understanding.

• Use for criminal offenses or for professional purposes such as medical use is prohibited. The model maker is not liable for any negligence due to non-fulfillment of the license.

• The CreativeML OpenRAIL license permits the sale of models and derivatives, but does not recommend the sale of models because it is currently an open access license. The creator of the model will not be held responsible for any problems that may arise from the sale of the model without the author's permission.

License

This models license is FLUX.1 [dev] Non-Commercial License

描述:

Recommended Settings

• WebUI Platform : ComfyUI

• ModelSamplingFlux

  • MAX_SHIFT : 1.0 - 1.1 (Recommended : 1.05)

  • BASE_SHIFT : 0.0 - 0.1 (Recommended : 0.05)

• FluxGuidance : 2.5 - 3.3 (Recommended : 3.0)

• Steps : 20

• CFG Scale : 1.0

• Sampler : euler

• Scheduler : normal

• Denoising : 0.8 - 1.0 (Recommended : 1.0)

• Resolution : 1024 x 1536

训练词语: