Loaded
Download
1 variant available
The creator of this LoRA has set this version to Early Access and as such it is only available for people who purchase it. This LoRA will be available for free in . If you want to know more, check out our article here.
Notify me when it's available.200 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
10 1 2 3 4 5 6 7 8 9
1310 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(38)
Oct 11, 2026
MiniMax H3

1.2K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
6.8K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
49.8K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

License:
On Civitai (generation, training, sharing LoRAs):
covered by Civitai’s agreement with MiniMax
The MiniMax H3 Community License Agreement’s grant excludes the European Union, the United Kingdom, the Republic of Korea and the United States of America.
MiniMax H3
A LoRA inspired by one of my favourite styles of hyperdetailed colored pencil illustrations.
This style captures the intricate shading and fine textures, enhanced by the subtle depth and warmth of colored pencil strokes.
Ideal for creating striking portraits with expressive details, this style brings out the natural beauty of facial features, elaborate clothing, and delicate embellishments. It blends artistic sophistication with a touch of classical elegance.
The keywords are ArsMJStyle, Colored pencil hyperdetailed realism.
MiniMax H3:
This version is trained on the images from V2 Dataset. It's a style LoRA, so its video strength comes from locking it into every frame and preventing style drift .
Best results: FL2V or hybrid workflows (T2I → I2V/FL2V, T2V/FL2V).
Gallery: Both T2Image and T2Videos generated with various workflows, with and without Turbo settings. All ComfyUI are preserved and you can check them out.
Note: Turbo LoRAs tend to diminish the effect of the style, when combining them, raise this LoRA's strength above 1.2 (e.g., 1.2–1.7).
V2 Update:
I simply love this LoRA , so I've been steadily extending the dataset with more diverse images , while trying to maintain the Original Concept.
It is more flexible than V1 , but with just a slight sacrifice for the Style Strenght.
Use V1 for stronger Effects or V2 for greater flexibility .
MidJourney V7 Update:
A complete rework of the LoRA’s dataset using MidJourney V7 for improved versatility and future expansion. The original aesthetic has been preserved as best as I can after switching models, with a shift toward more realistic rendering.



