egpieper
Merged Flux Models
ABSTRACT_PIANTER_V1
This Flux Model is a merge that has its weights altered so severely that is can only generate abstract, impressionistic and surreal paintings.
It generates dots and strokes and losely gives an impression what suppose to be drawn according to the prompt.
REALISTIC_V1
This Flux Model is a merge of 50% JibMixFlux_v7PixelHeavenBeta and 50% Flux_Dev with DarkSunRiddV4 Lora (and an unpublished trained Pieper_FLUX_LORA).
It tends to downgrade the (over)detailing in the JibMixFlux_v7PixelHeavenBeta model a little so it provides less abnormalities in the output on everything not being female. It gives less artifacts on armor and clothing and machines, but still is superior over the basic Flux.Dev base model and generates perfect female portraits with smooth skins. The Pieper_FLUX_LORA will tend to give more realism on the male face portraits. Overall it generates more bokeh on backgrounds as prompts demand this and makes the subject pop-out a little bit better.
Note: JibMixFlux is one my favorite models for realistic output. This is not an attempt to highjack someone elses hard work. I was just tinkering with a local model merge workflow in ComfyUI and this result surprisingly turned out very stable on outputs.
I just wanted to share this model and this model type is discontinued for me. I will focus on a different type of models. Once a superiour model of JibMixFlux comes out I might remove this Realistic_v1 Model from CIVITAI.
Comparison with same seed and settings:
What is Pieper_Flux?
Pieper_Flux is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user egpieper. Derived from the powerful Stable Diffusion (Flux.1 D) model, Pieper_Flux 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 Pieper_Flux is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as abstract, base model, realistic.
With a rating of 0 and over 0 ratings, Pieper_Flux is a popular choice among users for generating high-quality images from text prompts.
Can I download Pieper_Flux?
Yes! You can download the latest version of Pieper_Flux from here.
How to use Pieper_Flux?
To use Pieper_Flux, 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 Pieper_Flux, check out our crash course in AI image generation.
Popularity
Info
Latest version (Realistic_v1): 1 File
About this version: Realistic_v1
This merge focuses on realistic output.
This Flux Model is a merge of 50% JibMixFlux_v7PixelHeavenBeta and 50% Flux_Dev with DarkSunRiddV4 Lora (and an unpublished trained Pieper_FLUX_LORA).
It tends to downgrade the (over)detailing in the JibMixFlux_v7PixelHeavenBeta model a little so it provides less abnormalities in the output on everything not being female. It gives less artifacts on armor and clothing and machines, but still is superior over the basic Flux.Dev base model and generates perfect female portraits with smooth skins. The Pieper_FLUX_LORA will tend to give more realism on the male face portraits. Overall it generates more bokeh on backgrounds as prompts demand this and makes the subject pop-out a little bit better.
2 Versions
Go ahead and upload yours!
