Read Description

Questions/Feedback/Updates

Visit my thread on the Unstable Diffusion Discord

Buy me a coffee ❤

https://ko-fi.com/ndimensional

All donations will be used to fund the creation of new Stable Diffusion fine-tunes and open-source AI tools.

Like photorealism? Try my new fine-tune 'Lomostyle'

How about art? Try my new fine-tune 'Doomer-Boomer'

VAE not required but recommended

VAE is recommended - https://huggingface.co/stabilityai/sd-vae-ft-mse-original/tree/main

File Structure for AUTOMATIC1111-webui :

|──sd

|____|──stable-diffusion-webui

|____|____|──models

|____|____|____|──VAE

|____|____|____|____|──<Put your VAE file here>

Merged Models

A list of merged models can be found bellow in the description of the attached model version.

This model used an unconventional method of merging, more information available in the models description.

This model is experimental

Capabilities

• NSFW/SFW portraits

• Photorealistic 3D renders

• Landscape and Architecture photography/renders

• Emphasis on photorealism and detail

Limitations

Anything not listed above. I'm unsure of how this model will handle stylized images, admittedly I'm not great at writing stylized prompts. Please do test and share your findings!

Trigger Words

I'm not aware of any trigger words that have drastic influence on the generation process.

However, tags such as:

"3d render", "cartoon" | "nsfw", "sfw", "nudity", and "erotica"

tend to add push the generation (to some degree) in one direction or another. For example, putting sfw in your prompt and nsfw in your negative prompt should push the generation to produce a SFW image.

Prompt Guide

UnstablePhotorealv.5 was used in this merge, as a result comma separated tags can achieve decent results. Although I recommend using a combination of separated commas + the natural language flow you're likely more familiar with.

Refer to this document for more information on UnstablePhotoreal tagging - https://docs.google.com/document/d/1-DDIHVbsYfynTp_rsKLu4b2tSQgxtO5F6pNsNla12k0/edit#heading=h.3znysh7

For v4 :

If the sample image's prompt includes AND_PERP or AND_SALT; you need the Neutral-Prompt extension for A1111 (webui) to replicate the image.

link to extension - https://github.com/ljleb/sd-webui-neutral-prompt

Set the custom CFG slider in the extension to 0.5

What's Next?

• Fine-tuned dreambooth models that focus on areas current SD models fall short.

• Hypernetwork, or tuned decoder for better handheld object holding.

• Fine-tuned dreambooth model for firearms and various other weaponry. (This ties in with the aforementioned Hypernetwork).

• R&D for LoRA.

• R&D for new methods of merging.

• Miscellaneous scripts and utilities that I create while working on SD-related projects.

• Text-to-inpainting extension for AUTOMATIC1111 webui

Checkout my other models

SDXL

• LomoXL - https://civarchive.com/models/156743/lomoxl

• Boomer Art Model - https://civarchive.com/models/163139/boomer-art-model-bam

SD1.5

• Doomer Boomer - https://civarchive.com/models/118247?modelVersionId=128239

• Lomostyle - https://civarchive.com/models/109923/lomostyle

• Based Model - https://civarchive.com/models/83991?modelVersionId=89262

• Electric Eden - https://civarchive.com/models/64355/electric-eden

• Cine Diffusion - https://civarchive.com/models/50000/cine-diffusion

• Eris - https://civarchive.com/models/21952/eris

• Project AIO - https://civarchive.com/models/18428/project-aio

• WonderMix - https://civarchive.com/models/15666/wondermix

• Refined - https://civarchive.com/models/8392/refined

• Experience - https://civarchive.com/models/5952/experience

• Clarity - https://civarchive.com/models/5062/clarity

• VisionGen - Realism -https://civarchive.com/models/4834/visiongen-realism

LoRA

• Pant Pull Down - https://civarchive.com/models/11126/pant-pull-down-lora