take a look at my Patreon Chamber | 3d Asset, Dev Tool, Game | Patreon,
Subscriptions can help me update further and create more~
there are detailed posts and assets and I am willing to help if needed~
1. for better results, a suitable CKPT is important, I think the CKPT samples used above like Mistoon, anything, CO3, and Maiji series are good starts, then test, merge, or train for different cases/projects,
2. the prompts behind (general:0) are important,
3. use at least 2 Turn LoRA, the main one weight around 0.7, and the secondary one weight around 0.15 is one of good strategy, test the weight and element for better results please,
4. the resolution should be 768*512 then upscale, because of the train data, personal sample setting: Euler A, 20 steps, R-ESRGAN 4x+ Anime6b, denoise strength 0.3, upscale by 1.25, CFG 7, clip skip 2, anything VAE,
5. turn on after detailer,
6. turn on CtrlNet OpenPose, 0.6, pixel perfect, pick one of the samples above as input,
If you are interested in or want to download
more my personal LoRAs merged checkpoints for game design
the raw generated image with generation info,
LoRA training preset files,
raw pictures data training set and tag preparation,
prompt structures
and how to model these images to 3d models,
take a look at my Patreon Chamber | 3d Asset, Dev Tool, Game | Patreon,
Subscriptions can help me update further and create more~
there are detailed posts and assets and I am willing to help if needed~