Hello everyone!
All models are exclusive to Civitai ! Anyone who publishes my models without my consent will be reported!
Trigger Word : Anime style
I highly recommend loading my lora models in fp16 if possible
Since Flux's anime style is a bit weak, I decided to tackle it for my first training of Flux LoRa model.
v3_Final : This version uses the same dataset as v3.1 but this time at 100 epoch against 16 before.
The poses are more dynamic and the characters more expressive
V3.1 : A new dataset of 330 images. Better selection so that characters look older if requested.
The overall quality is also much better
V2_Final : same as v2_15k, but the style is much more pronounced
v2_15k : This version has a dataset of 338 images against 112 for version 1.
This is not the final version of this v2, but I find this 15k steps version very interesting and rather stable.
This version was trained with the optimizer "prodigy" in rank 32
The style is there, but the final version will be very different!
V1 : I used for this 112 high quality images generated with MidJourney v6 in the --personalize style.
Be indulgent, this is a first try. If you zoom in a bit on the images the lines can appear a bit pixelated. But the style is pretty cool!
For a pronounced anime style, Sweet spot between 0.90 and 1.30
I recommend you to play with the strength to vary the pleasures for example at 0.5 or 0.6 by asking for a realistic image.
The model was created with Ostris script which you can find here :
https://github.com/ostris/ai-toolkit?tab=readme-ov-file#flux1-training
Have fun! 😊
Description
FAQ
Comments (10)
looks pretty amazing 9.9/10
Many Thanks 🙏
"don't steal my model trained on all of these stolen images" Your lack of self-awareness is hilarious XD.
I train my models with Niji and MidJourney images that I paid for!
i think someone uploaded your lora in tensor art
Thank you for letting me know.
It's because of these people that I haven't published any models in almost a year.
I've created some incredible Loras, even checkpoint ones.
But you're deprived of them because of them!
Stan_Katayama you can just claim your lora there and it will be fine
Stan_Katayama or you can contact mod on there discord they will help you
onlysharma0852 I did it at first. But it's very humiliating to have to constantly justify that our work is our own.
And moderation on sites like Tensorart is almost nonexistent.
@Stan_Katayama don't worry you can open a ticket on there discord channel. You need to provide your civitai profile to them and they will claim your lora back to yourself. But please make a account on tensor art first. I know it's frustrating but we can't do anything about these theifs. I hope you understand. Btw love your work you are doing a great job ❤️
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.