This is a personal merge, for whatever reason I decided to make custom covers for my Webnovel collection in Calibre, I was just wasting time, but I was met with a problem, 1girl face, it was becoming a problem, I usually use Fooocus, so I do a lot of inpainting to maximize details and try to make great cover arts, which was making 1girl face a bigger problem.
Anyway after days of wasting time, this is what I got, I deleted few other versions because merging loras or other models was taking up too much space. I like this version a lot so more than sharing I am saving it, maybe even use this model to train lora in the future on Civit.
Just your regular pony scores should work, what i have been using is. I really dont see too much difference, other than seed change, but I still do it for the placebo.
I usually first make the image in Eular A and then upscale 1.5 with heun
Positive Prompt: score_9, score_8_up, score_7_up,best quality, high resolution, best quality, highres, realistic, beautiful, detailed, rating_questionable,
Negative prompt: score_6, score_5, score_4, low quality, low resolution, worst quality, low quality, lowres, bad quality, blurry, film grain, bokeh, bad art, bad artist, bad composition, text
NOVEL MIX is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user TIGERACE. Derived from the powerful Stable Diffusion (Pony) model, NOVEL MIX has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that NOVEL MIX is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as sexy, style, woman.
With a rating of 0 and over 0 ratings, NOVEL MIX is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of NOVEL MIX from here.
To use NOVEL MIX, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like NOVEL MIX, check out our crash course in AI image generation.
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.