Sign In

Flux-Better-Art-With-Niji

1k

Updated: Oct 11, 2024

styleanimephotorealisticartgirlsmale

Download

1 variant available

SafeTensor

327.88 MB

Verified:

Type
LoRA
Stats

1,010

1K

2K

Reviews
Published

Sep 25, 2024

Base Model

Flux.1 D

Hash
AutoV2
472946CA51
Trigger Words
niji
default creator card background decoration
Followers - 10176

10.2K

Likes - 55133

55.1K

SDXL Training Contest Participant

The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.

IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

xyz_grid-0066-3325229595.png

you like my content, support me at:

https://ko-fi.com/duchaiten

Patreon in here:
https://linktr.ee/Duc_Haiten

I
created my discord server. I'm still quite new to discord server management, free to give opinions.

https://discord.gg/FPhQvFsqe2


The same dataset trained on Dev and Schnell seems to perform better on Dev, as it shows fewer anatomical errors, more accurate colors without being overly saturated, and sharper, more precise details. It is also more flexible and diverse with the same prompt and random seed. However, it trains slower than Schnell, has less artistic quality, and doesn't learn as closely to the training data as Schnell does. Sometimes Schnell appears to adhere to the prompt more strictly, and I think this might be because Schnell works better with a lower CFG than Dev, which causes this phenomenon. Currently, there are ways to increase the true CFG for Dev, but it’s said to increase image generation time, and so far, this can only be done on ComfyUI.