Thank you for all your support!
Welcome to the Next Era of Finetuning with Flux1!
[ See Before and After ] I’m back and diving into the new wave of model finetuning with Flux1. If you’ve enjoyed my previous work, you’re going to love what’s coming next. To help you get started, use the following workflow with Scheduler Beta at 30 steps: https://rpgv6.byecho.ai/RPGv6-Beta3.json
Want to help? Get free access to Flux1 and GPT-4o by claiming your key on my RPG Discord.
Dive into building entire RPG campaigns, character sheets, artwork, landscapes, and more. Or, join me as we work on training RPG v6 together. We’re a new and growing community, pushing the boundaries of RPG prompting. We're on the lookout for leaders and top-class prompters to join us on our Discord!
Iteration Process
If you've been following my RPG v5 series, you know I’m all about my iterative process. I typically go through around 35 iterations before finalizing a release.
Model Details
Fully trained on 1024-pixel images
100% original content, no merges
Focused on RPG character creation
For Fellow Training Enthusiasts
I’m sharing a Docker template of SimpleTuner for RunPod with all my fine-tuned settings. Perfect for those looking to replicate or build upon my process.
Past release: RPG v5 for SD 1.5
Description
20 new Concepts grouped in 9 categories ... and My LORA is having a hard time keeping up. :)
--
Use the following Comfy Workflow for better result. https://rpgv6.byecho.ai/RPGv6-Beta3.json
Trying new approach for Beta 4, stay tune. In the meantime, have fun:
- Fire Mage
- Frost Mage
- Elf Archer
- Human Warrior
- Human Paladin
- Drown Elf
- Dwarf
- Plate Armor
- Leather Armor
FAQ
Comments (16)
I enjoyed beta 2 and was going to write it when I saw beta 3... Pff but rest a little people! ^^^
Come on, have to go play, uh test phuuuuu...
Lol, thanks... and yeah, I need to rest a little. :)
With version v6.0 Beta 3 it is almost impossible to generate a Skaven creature. Still, really great work. Thank you!
Yeah, I see that my original 'concept' have faded out. I am trying to figure out the best approach as I add more concept. I mage to get some good one, i'll share the workflow, prompt and seed ID.
Oh your the one who gave me a tips, thank you!! :)
would you keep in mind 'training data' the vintage mmorpg's ? AND put that as SDXL model ?
thanks !
Vintage MMO, can you give an example, do you mean WoW? All the asset are original content, so I cannot use their assets.
@Anashel i will sent you a specific game name in a mesage , if you interested in making a model based on it , i can supply you with good picked pictures 'much..' to make it as dataset .
..it's still alive anyway and very active game , all people played it still obsessed on it
@Anashel absolutely not wow !!...
@amazingbeauty Sure!
Really cool Lora,Thanks!!
Thanks!
Very noticeable how different versions seem to handle things well that the others have difficulty in... while some think of this as a curse, wanting there to be a "one stop shop" version (which is a of course an admirable goal), I do like the idea of "the right tool for the right job", each one mastering its particular specialty. And these do well... once you find the right version for your goal. (I agree with another commenter... #2 is the one for you if Skaven is your goal! Such sexy nasty rats. :) )
From limited testing, this Lora (v6 beta 3) does a very good job of sticking to the original prompt/output while adding additional coherent detailing. A very nice Lora.
Thank you!
Very excited for the launch!
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.