Frankenstein - Model Suite: Experimental Grounds

• Warning: Highly Experimental Models Ahead! Proceed with Curiosity (and Caution)!
  

Welcome to the laboratory! The Frankenstein Model Suite is where I unleash my more... unconventional creations. Unlike my refined models such as Everlasting, the models hosted here are born from experimental merges, unusual training techniques, bespoke modification scripts, and sometimes, sheer chaotic curiosity.

Think of this as a collection of works-in-progress, oddities, and boundary-pushing attempts. They are stitched together using various methods, potentially including techniques developed with my custom-crafted merger tool and other experimental approaches

Methods

Block Swap (BS - Custom Merger Implementation): Instead of blending weights, this method swaps entire architectural blocks (like input, middle, or output sections of the U-Net) between models based on certain rules. It aims to combine functional strengths but risks incompatibility between the stitched sections. (HIGHLY EXPERIMENTAL BUT FUNCTIONAL)

Latent Resonance Tuning (LRT): Attempts to identify key latent features in one model and subtly amplify corresponding weights in another, trying to make the second model "resonate" with the first model's specific strengths at a feature level. (EXPERIMENTAL)

Gradient Harmonic Injection (GHI): Involves injecting scaled gradients from a parent model during a post-merge fine-tuning phase, attempting to subtly steer the merged model towards a parent's style without full retraining. (EXPERIMENTAL)

Cross-Attention Splicing (CAS): Mixes components of the cross-attention mechanism (e.g., query/key matrices from one model, value/projection from another) to blend how models interpret prompts with how they apply that interpretation. (EXPERIMENTAL)

Denoising Path Scaffolding (DPS): Uses parts of a parent model's U-Net to temporarily guide or replace calculations at specific steps within the merged model's denoising process. (EXPERIMENTAL)

What to Expect:

Unpredictability: Results can vary wildly. What works for one prompt might break on another. Expect the unexpected!

Potential Instability: Some models might produce artifacts, glitches, or struggle with coherence more than polished releases. Hands, feet, and eyes might be even more challenging than usual.

Niche Capabilities: A model here might do one very specific thing interestingly, but be terrible at everything else.

Occasional Gems: Sometimes, the chaos yields surprisingly unique aesthetics or combinations you won't find elsewhere!

Why This Suite Exists:

This is a space for open experimentation and sharing explorations that aren't quite ready for a "stable" release. It's a chance to play with rougher ideas and see what strange beauty (or monstrosity) might emerge. Your feedback and discoveries – good, bad, or just plain weird – are part of the experiment!

Recommended Settings:

Highly Model-Dependent! There are NO universally recommended settings here. Check individual model notes if available.

Starting Point: You can start with common settings (e.g., Sampler: Euler a, Steps: 20-30, CFG Scale: 5-7, Clip Skip: 1-2), but be prepared to experiment heavily.

Prompting: Some models might require very specific trigger words or prompt structures. Others might ignore negative prompts entirely or react strangely to them. Pay attention to any included examples.

Denoising: For img2img or refining outputs, denoising strength might need careful tuning (try ranges like 0.5-0.75).

Usage Guidelines:

*Non-commercial Use:** Primarily intended for personal experimentation and non-commercial creative exploration. Please generate responsibly.

*Sharing:** Feel free to share your generations. If sharing the models themselves, please link back here and keep the experimental nature crystal clear.

*Attribution:** When sharing results, mentioning the specific model name and technique (if known) from the Frankenstein Suite helps track these experiments.

*Feedback Welcome:** If you find interesting settings, prompts, or use cases (or run into spectacular failures), sharing your findings can be valuable!

Dive in, experiment (safely!), and let's see what these stitched-together creations can do!