PLEASE POST GENERATIONS OF MY MODELS!
I can't keep producing LoRAs if y'all don't help me get Buzz!
Flux version of my AIO TMNT LoRA. This model was trained on a combination of about 300 images including different art pieces/styles and select movie frames from the first 90s TMNT movie.
Recommended keywords/tags:
In the event that the Turtle you are prompting for does not generate properly- i.e the wrong mask color- I highly recommend using the phrase "wearing (purple/orange/blue/red) bandana mask with eye-holes" but without the ( ) and /
Key triggers are going to be:
a teenage mutant ninja turtle
nunchucks
wooden fighting staff weapon
sai dagger weapons
sword, swords, sheathed swords on back
wearing ________ bandana mask with eye-holes
TMNTDonatello
TMNTLeonardo
TMNTMichelangelo
TMNTRaphael
TMNTGroup
TMNTLastRonin <--- (v3 Digital Art version only)
I trained at 1024 res and highly recommend hires fix
If you enjoy my work, please Like/Review/Upload your generations and if you're especially interested in supporting my work you can tip me some Buzz or support me on Patreon/Discord, I accept commissions for both Ai Assisted art and LoRA model creation as well as donations to assist furthering my projects. I don't have substantial cash flow to support pumping out models and am on an AMD Win 11 PC so training isn't an option locally, so if you're interested in assisting me further or want something special, let me know.
Description
This version can do much more realistic likenesses of thew turtles. I know people say Flux doesn't need a Negative prompt, but I feel enabling the negative prompt really enabled me to control my image more.
FAQ
Comments (10)
It's already fun to use :) I think the next step and maybe sort of challenge (?) will be the specific weapons (especially the SAIs, as FLUX doesnt know them).
Thank you for the Buzz! ❤️
That is going to be a huge challenge. One that I'm not sure I'm equipped to handle. It may take a very beefy LoRA trained on the weapons and holding those weapons in certain poses as concepts, then merging the LoRAs together? Or maybe require fine tuned base models of Flux including stuff like martial arts and proper melee weapon handling? These LoRAs were trained with extensive examples and thorough captions involving every weapon they use. And even so, both the digital art LoRA and Realistic+DigitalArt LoRA struggle to make anything that resembles proper TMNT weapons.
@ArchAngelAries sadly I dont know anything about LORA training - yet ^^ maybe it would be possible to train the weapons separatly and then merge them in? with my Leonardo with katana image it did at least work somehow (even the shoulder holster is empty ^^ ) but if FLUX doesn't know anything about a sai, training it with the turtle himself might be not enough?
wonderful, thank you
Happy to do it! Make sure to checkout both v4 and v3 and both have their strengths and weaknesses depending on what style you're going for. Thanks for your support!! ❤️
I've been working on creating a Leatherhead avatar. So far, your original TMNT LoRA was the best at honing in on his characteristics. I will share later if I can.. image upload seems to be broken atm. Thank you for sharing :)
Strange since I never trained Leatherhead in the dataset, but that's cool
@ArchAngelAries Thanks again for sharing this style, even though I wasn't using your trigger words, I really think it gave it the look and feel I was going for :)
I was able to post today! The image upload error was an issue on Firefox, but I was able to use Edge.
@anniemuse69 I'm glad you found my model useful! Even if it wasn't for the turtles themselves, I'm really glad to know my model assisted you in the style you needed 😊❤️
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.