Main characteristics of this LoRA are as follows:
· Reversal film / slide film style, with strong contrast and rich, intense color saturation.
· Improved lighting and shadow effects, especially extremely powerful and expressive sunlight rendering.
· Based on personal aesthetic preference, female characters tend toward large breasts, slim waist, and wide hips.
Important: This LoRA has a very strong style with distinct personal preferences. In other words, it cannot guarantee diversity in body types etc. (You can achieve more variety by using detailed and specific prompts.)
Info for MiniMax-H3-Image
Note: This LoRA is designed for MiniMax-H3-Image (T2I model), NOT MiniMax-H3 (video model).
Key Improvements:
• Improved lighting and shadow effects.
• More attractive female characters.
• Reduced the coarse graininess and jagged edges present in the original model.
Recommended Sampler: euler_simple
(This LoRA was trained using euler_simple. Using other samplers may reduce its effectiveness.)
Recommended Strength: 1.0–1.25
Important Tip: To reduce the roughness of the original model's output, it is strongly recommended to connect a blank white image to the MiniMax H3 Image Conditioning node.
The white image can be relatively small. For example, for a 9:16 aspect ratio, a resolution of 512 × 910 is sufficient.
Recommended Resolution: Generate images at 16 megapixels for the best possible image quality, then downscale them to your desired resolution as needed.
Info for MOSS-Image-Base v1.0
This LoRA was trained on MOSS-Image-base and can be used with lodestones/MOSS-Image-Base-8-steps-dmd. In theory, it should also work with the SFT model, but this has not been tested.
• Recommended Settings:
• Strength: 1
• Sampler: euler_sgm_uniform
Info for Flux.3 Klein v1.0
This Lora supports both base and step distilled model. NSFW supported.
• Recommended Setting:
• strength: 1
• sampler: euler_simple
License NOTE:
This LoRA is released under the FLUX Kommunity L