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
FAQ
Comments (8)
Please keep up bringing TMNT content, your work is great and unique!
When I first saw your lora for SD1.5 it was such a hit of nostalgia, based on the original movie (1990), probably the best of them all. I almost never use the loras but always download them, for all models.
Hopefully, Flux will become less resource demanding and you'll be able to generate/train more locally. And there's Pony v7 on the way (pre-training phase now), hopefully you'll do some loras for that too after some time of its release.
Good luck!
I'm really glad you're enjoying my work! And I super appreciate the buzz tip! It definitely helps me to keep refining things, and especially with support from those like you! :) <3
@green_anger Just released a new version for TMNT Flux! Digital Art style only but it turned out amazing! Still sucks for realistic though...
@ArchAngelAries I cannot harness flux loras =( There's probably something I'm doing wrong. I tried your lora but it can give random style with the same prompt (similar to the original pony v6). Plus with flux each lora I add slows down inference, e.g. with one lora it goes down from ~1.1 sec/it to ~1.7 sec/it on my rig.
I've seen many workflow examples that use loras but nothing out of ordinary, it cannot be that difficult. Kinda sad...
But I saw you published a new pony realistic lora, on the screens it looks so close to the original movie, congrats!
@green_anger Thanks! I've been slowly trying to perfect the Turtle LoRAs.
As far as Flux, it could be that my local install is using Forge webui with the Flux Dev fp8 and Flux Dev BNB N4 models on ZLUDA. I'm on an AMD WIndows PC so my generations with Flux take minutes rather than seconds. But the difference in which Flux base models might be what causes the style variety.
I have come to the conclusion that Flux sucks ass for realistic TMNT. Been training and testing all day and even when soley trained on live action movie stills only Flux still gives me crappy toys and 3d images resembling the TMNT 3d movie.
I had a similar issue with Optimus Prime. I think Flux is highly over trained on toys for certain subject matter.
Maybe use more unique trigger words for the turtles? There's probably TMNT stuff that already exist in Flux that conflicts with the actual look you're after
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.