THIS MODEL IS V-PRED
I tried merge model to give a 3D appearance while keeping the face in an anime style.
enjoy it!
🟦 Recommended Settings
Positive Prompt
masterpiece, best quality, absurdres, highres, anime coloring, 3D
Feel free to add shiny skin, humid skin to the prompt depending on your preferences.
Negative Prompt
lowres, bad quality, low quality, worst quality, text, error, fewer, extra, missing, jpeg artifacts, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, artistic username, scan, abstract, 4koma, surreal, abstract, dissolving, multiple views, grey background, sepia, futanari, furry, lips
🔧 Recommended Generation Settings
Sampler:
Euler a,DPM++ 2M SDEScheduler:
SGM UniformCFG Scale:
3–5Resolution Options:
960x12801280x9601128x1128832x12161216x8321024x1024
Sampling Steps:
24–30 stepsHires Settings:
Denoising Strength:
0.3–0.4Upscale Steps:
10–15 steps
Description
color overexpression fixed
presence or absence of the ‘3d’ tag now creates a clear visual difference
overall texture quality has been refined
FAQ
Comments (3)
You know... i've always wondered.. is there some way to PRE load a checkpoints settings? Like how with a LORA you can put prompts that, when you click the lora, it auto places the prompts....
SO for like a checkpoint, it auto places the settings? I tend to use a lot of checkpoints, specifically for different styles or 'species' so being able to load the 'optimal settings' by activating it would be very nice...
I ask because I don't know.
In the case of WebUI, it might be possible to achieve similar functionality through extensions, but it’s not supported by default. However, you can use a similar approach by either loading the EXIF data from the PNG Info tab to recall the generation settings, or by saving prompt presets for later use.
@zzkz Fair enough. I usually use PNG info to get a base as it is. I'll at the least keep a txt file with it so i can grab it even if my internet is down. Thanks for the reply.