license: cc-by-nc-4.0
MzPikas TMND Enhanced
experimental Attention Agreement Score merge model
Using the sum of negative DAAM cumulative attention scores from teacher models as loss, running neuron-wise merge with AdamW from four teacher models, trained on images with resolution 2048x2048
https://civitai.com/models/27259/tmnd-mix
https://civitai.com/models/47067/pikas-new-generation-v10
https://civitai.com/models/31383/mzmix
https://huggingface.co/Xynon/SD-Silicon/tree/main
Model does not yield satisfactory result below resolution 2048x1024 during tests.
Tested workflow:
t2i 1024x512 x2 hiresfix output 2048x1024
i2i multidiffusion Euler a or DPM++ 2M Karras x2 Ultrasharp Denoising strength 0.35-0.4 output 4096x2048
Slight face/limb distortion under t2i result can be fixed automatically in i2i step
reduce the weight of silicon isolation Lora/reduce the overall weight of background prompt/increase the overall weight of character prompt if foreground character does not appear.
Demos:
Images without metadata are too large for upload as PNG. I'll post them in Discord.
Lora used is included in repo.
