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
OC 1024-pixel model with 15,000 training cycles across 10 iterations of fine-tuning is now complete. We are now expanding the Skaven content to include more general RPG elements, such as armor and plate.
FAQ
Comments (5)
Flux? Not interested. - Is what I've been saying all this time, until I saw this post! I was starting to think RPG project was getting abandoned! 🤩
And now I must join the hype... Fine. Have a 'like', damn you...
Lol!!! If you are master at SD 1.5 with very advanced workflow and LoRA, you may not have right away better result with basic prompting on Flux1 Dev. I am running Flux1 Pro and honesty the difference is impressive. I can only imagine what people will be able to do with more advanced workflow. I should publish a new RPG version today for Flux1 Dev. If you test it, let me know how it goes! :)
FLUX adherence in trainings are x10 to SDXL or SD1.5. I suggest to take it seriously :)
@LDWorksDavid It's not even about that. In truth, I was going over papers by Rombach, Blattman, and others when Flux came out. I wanted to understand Stable Diffusion better, and what is 'under the hood'. I didn't want to get distracted by Flux.
And then... Then I realised that Flux is actually made by these same people whose papers I've been studying. People left Stability AI.. The CEO has also left... What the hell is going on. I don't follow the politics all that closely. Like I lived under a rock for a few months...
@Anashel Yep, just like SDXL, Pony, Lightning, etc. etc., each big family change in base models clearly wants us to speak just a wee bit different dialect to convey our desires. We just have to learn it. I despised them all until I figured out the 'language', now I appreciate them more. Well, maybe not Pony as much... even knowing the language, it's still a cantankerous moody [censored] half the time! <lol> This is one more encouragement for me to play with Flux a bit more.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.