Verified: 9 months ago
SafeTensor
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.
This is a mix of different artist styles from NAI, the mix is :
[artist:ningenmame], [artist:ciloranko], [artist:sho{{sho_lwlw}}], [[artist:tianliang_duohe_fangdongye, artist:as109]]Dataset of around 60 images made from NAI with that artist mix, each images was then reworked and any issue was fixed with either inpainting or GIMP.
Tagging was done using the structural settings with PromptGen v1.5 large model and reviewed manually.
There is no trigger word. But if the result looks too realistic, just add "in a manga style" and that should fix it.
The training settings (you'll need at least 24Gb vram for it) and captions I used can be found in the training data zip, training was done with LoRa_Easy_Training_Script.
Sometimes body proportions are a bit weird legs/torso, hands tend to not look that good on far shots, inpainting works well to fix those issues.