[Some example images have generaited through 'SDupscale' process]
use vae : vae-ft-mse-840000-ema-pruned.safetensors
CamelliaMix_V3 update
Still not good hands
▼Please check settings and prompts▼
Merge model (V3)
CamelliaMix_V1
CamelliaMix_V2
Dal_rose_merged(Unshared Merge Model)
CoNiCa_UMOKA(Unshared Merge Model)
Recommended setting
Sampling method : DPM++ 2M Karras, DPM++ SDE Karras
Clip skip : 2
Hires.fix upscaler : R-ESRGAN 4x+Anime6B(Option)
CFG Scale : 5~10
Recommended prompt
Negative : (worst quality, low quality:1.4)
Textual Inversion : negative_hand Negative
Description
FAQ
Comments (7)
Great model！！！by the way，are you have plans to update CamelliaMIx_2.5D in the future ？
Hi, do you change the seed when upscaling it? I can't seem to regenerate the same photo as you.
안녕하세요, 업 스케일링 할 때 씨앗을 바꾸나요? 나는 당신과 같은 사진을 다시 생성할 수 없는 것 같습니다.
It doesn't change generally. but, there may be differences in denoise strangth, or differences in negative embedding.
This is honestly the BEST model I've ever used. Model helped us create characters for tabletop games. I mean from dnd to cyberpunk. It does it all! I wish all the best to the author.
Sorry but can you share about your upscale process?
Details
Files
camelliamix_v3.safetensors
Mirrors
camelliamix_v3.safetensors
camelliamix_v3.safetensors
camelliamix_v3.safetensors
camelliamix_v3.safetensors
camelliamix_v3.safetensors
camelliamix_v3.safetensors
camelliamix_v3.safetensors
CamelliaMix-v3.safetensors
CamelliaMix_V3.safetensors
camelliamix_v3.safetensors
camelliamix_v3.safetensors
camelliamix_v3.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.