Donate for civilians in Ukraine, Syria, Mali etc.: Red Cross | Doctors without Borders | DirectRelief | Feed The Children
My favourite 2.5D (aka semirealism) model. The goal was to create a model that is accurate, versatile, aesthetic but does not over-emphasize the anime face.
πΈ Can do both NSFW and SFW without issues. As a headsup, the word solo in the positive prompt seems to steer models towards NSFW.
πΈ Highres Fix recommended, for example: Latent (Nearest-Exact), Scale 1.5, Denoising strength 0.55, 25 Steps with DPM++ 2M Karras
πΈ Controlnet with OpenPose recommended for anything depicting characters.
πΈ No trigger words needed but I particularly like results with prompts including realistic, photo, photorealism, oil painting, masterpiece and diffused soft film lighting.
πΈ Suggested negative prompt: ugly, blurry, low quality, bad quality, worst quality, low resolution, lowres, bad anatomy, deformed, (child, loli:1.3), bad hands, mutilated hands, missing fingers, extra fingers
This mix was a ton of work with probably 10+ iterations and changes in the 2.5 % range. I hope you enjoy the model as much as I do xx
Credits: MeinaMix by Meina, RealDosMix by DiaryOfSta, RealisticVision by SG_161222, Offset Noise Lora by theovercomer8
The rather restrictive license is inherited from some of the models the mix, it's not on me.
Fidelity π is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user festival. Derived from the powerful Stable Diffusion (SD 1.5) model, Fidelity π 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 Fidelity π is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, character, girl.
With a rating of 4.93 and over 15 ratings, Fidelity π is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of Fidelity π from here.
To use Fidelity π, 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 β 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 Fidelity π, check out our crash course in AI image generation.
Go ahead and upload yours!
Your query returned no results β please try removing some filters or trying a different term.