A merge that is meant to generate semirealistic images with nice aesthetic and composition. Example images did not use Hi-res fix, refiner, or Adetailer because my machine is a potato. Feel free to provide feedback on the look of the model. Do people prefer more realistic or more stylistic outputs?
Resources used:
CLIP: NO MERGE - Universal CLIP by @Felldude - This should improve natural language, but tags are still preferred.
Models in the mix:
Plant Milk Walnut by @Ocean3: Everybody loves this style, including me
Illustrij EVO by @reijlita: Nice character aesthetics
Hyphoria [Illu & NAI] by @ecaj: Reinforce character knowledge and help with prompt adherence
JAVn - Real Merge - Envy IL by @WeBeJavn: Realistic Illustrious models usually have a certain default face shape. This is one of the models where that default shape is less prevalent.
Settings:
Steps: 25
CFG: 4
Sampler: Euler a
Scheduler: exponential
I am no expert so feel free to share better settings for generation. I also use Lazy Embeddings by @janxd. Add photo-realistic, realistic shading, realistic texture to the prompt if you want more realistic output.
What to improve:
Eyes and fingers can be messy sometimes.
Character knowledge is inconsistent.
Kinda Real Mix is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user nickname45. Derived from the powerful Stable Diffusion (Illustrious) model, Kinda Real 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 Kinda Real Mix is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, base model, woman.
With a rating of 0 and over 0 ratings, Kinda Real Mix is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of Kinda Real Mix from here.
To use Kinda Real 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 Kinda Real Mix, check out our crash course in AI image generation.
Changed the merge to use Illustrij - v17 instead of EVO. Added dmd2-lighting8step_cfg1.5 to speed up the generation on my slow system. Overall, there should be a noticeable improvement in textures, composition, and speed.
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.