Verified: 10 days 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.
Pala N: Enigmatic Operative
Agent from an isolationist state, serving as assassin, bodyguard, spy, diplomat, and agent. Erratic and capable, little can cause her loyalty to waver. Would you like to know more?
[Flux.2 Klein 9B]
Realistic (fictional!) concept for Pala N. New Flux training. Pala is the trigger - model mostly keeps her face consistent so prompting for blunt bangs and bright eyes can be useful for that extra push. Tested between 0.8 - 1.5 strength. Enjoy!
Data was created through Nano Banana Pro - first a face was composited and edited, then training images were generated. I would consider this a prototype but the results are very good! I hope you enjoy.
[Z-Image]
Realistic (fictional!) concept for Pala N. Z-Image training went very well despite me not having a lot of experience with captioned Loras. PalaN is the trigger - model mostly keeps her face consistent so prompting for blunt bangs and bright eyes can be useful for that extra push. Tested between 0.8 - 1.5 strength.
Data was created through Nano Banana Pro - first a face was composited and edited, then training images were generated. I would consider this a prototype but the results are very good! I hope you enjoy.
[Illustrious]
Same dataset as Pony[v2] but with all the added greatness of Illustrious. Training went very well, character is well defined with nothing but the Pala N trigger tag. Plays well with styles and actions and other LoRAs. Occasionally strays on hair colour so if you want her to keep her blank hair, black hair might sometimes be useful.
Tested mainly at 1.0 strength (in theory could lower it if anything causes issues) with both Euler A and DPM++ 2M Karras, but theory states it should work with whatever you personal preference is. Have fun and enjoy!
[Pony]
Working as usual, tags like brown skin and small breasts help keep it aligned. Lower strengths ~0.85 are what I usually use. Version 2 has somewhat less embedded style and seems to stay closer to the original character over many tests alongside clearer prompt adherence. Enjoy!
[Creator Notes]
Everything I make is for one purpose - fun. I don't mind not knowing much about AI (tbh don't even really understand how I managed to install A1111/Forge, Git is an enigma to me) , it allows me to create, learn, and grow. Personal projects are fountains of enjoyment for me, and in sharing them I hope to share some of that with the world - hopefully someone else feels inspired to create something!