Leosam's MoonFilm | Film-like realistic large model

0
0
0
0
RealisticStyle & FilterGirlStyle BoostLandscape
Recently Updated: First Published:
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info
Realistic,Style & Filter,Girl,Checkpoint,SD 1.5Image info

🤝 If you have model customization or other cooperation or consultation needs, please contact WeChat: 13439222668. Please simply indicate your intention

. Time is precious and don't chat casually. Thank you for understanding!

This is a large Checkpoint model for generating realistic AI photos. Its predecessor was the MoonMix series big model I posted at C station. The new version of MoonFilm is a fine-tuned large model using the expanded FilmGirl-style LoRa image training set and trained using Dreambooth. The realism of its portraits has improved significantly, so if you really want the realistic texture of AI photos,

be sure to try out this big model! It is also recommended to use the INVERSION model: bad_pictures,

negative_hand Negative Embedding. While these two negative embedding models do not significantly affect the image texture, they can play a good role in image correction and optimization

effects.

2023.7.9

updated Film Grain 2.0. In the production process of this version, we compared and tested the differences between the bottom model fusion Filmgirl Lora and the effects of using Filmgirl Lora for Dreambooth training, and the two major models were fused and hierarchically adjusted. After many rounds of testing, Film Grain 2.0 works better than 1.0 in terms of portrait beauty and skin tone

.

Also, in the landscape diagram shown in this model, the hint for the ice field aurora scene comes from blogger Sam Hui, which is indeed quite beautiful. Using this as a reference, I've also generated some other schematics of the scenery,

so thank you!

Updated Film Grian version 2.0. During the production process of this version, I introduced tests by introducing Filmgirl Lora into the base model and using Filmgirl Lora's training set for Dreambooth training. Then I merged the two large models examined, and carried out hierarchical weight adjustment. After multiple rounds of testing, Film Grain 2.0 is better than 1.0 in terms of portrait aesthetics and skin tone.

Paintings, the landscape sketches displayed in this model, including the glacier aurora scene inspired by the keyword from blogger Sam Hui, are indeed quite BEAUTIFUL. Taking this as a reference, I have also generated some other landscape sketches, and I would like to express my suggestions here!

Discussion

Most popular
|
Newest
Send
Coming Soon
Download
(0.00KB)
Version Details
Type
Generation Count
0
Downloads
0
Recommended Parameters
Sampler method
CFG
7
VAE
None

Gallery

Most popular
|
Newest