Read Description
Like photorealism? Try my new fine-tune 'Lomostyle'
TRIGGER WORDS ARE NOT REQUIRED
Trigger words are optional. I find they work best at the beginning of the prompt.
Known Trigger Words : "bldrnrst", "analog style", "synthwave", "snthwve style", "sci-fi", "postapocalypse", "nsfw", "sfw", "erotic", "erotica", "3d render"
Note: "nsfw", "erotic", and "erotica" can be placed into your negative prompt to generate SFW results.
There are likely more trigger words, experiment and share your findings!
Merged Models
A list of merged models can be found bellow in the description of the attached model version.
Check out my other models
SDXL
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
Project AIO - https://civarchive.com/models/18428/project-aio
WonderMix - https://civarchive.com/models/15666/wondermix
Experience - https://civarchive.com/models/5952/experience
Elegance - https://civarchive.com/models/5564/elegance
LoRA
Pant Pull Down - https://civarchive.com/models/11126/pant-pull-down-lora
Questions or Feedback?
Description
VAE IS REQUIRED
https://huggingface.co/stabilityai/sd-vae-ft-mse-original/tree/main
Models Used
Realistic Vision V1.2 - https://civitai.com/models/4201/realistic-vision-v12
Protogen x3.4 (Photorealism) Official Release - https://civitai.com/models/3666/protogen-x34-photorealism-official-release
ZombiMix-v8 - https://huggingface.co/zombihed/ZombiMix-v6
3DKX_1.1 - https://huggingface.co/HavoAloe/3DKX_1.0b
Art & Eros (aEros) - A tribute to beauty - https://civitai.com/models/3950/art-and-eros-aeros-a-tribute-to-beauty
Unfortunately I lost the exact recipe for this merge but it was started with the recipe from URPMv1.2 (https://civitai.com/models/2661/uber-realistic-porn-merge-urpm). I then made small tweaks as I tested each merge.
License is inherited from merged model witch itself inherited the license from one of it's merged models. Will be fixed in my next model.
https://huggingface.co/dreamlike-art/dreamlike-photoreal-2.0/blob/main/LICENSE.md
https://huggingface.co/dreamlike-art/dreamlike-photoreal-2.0
FAQ
Comments (13)
"Small natural breasts", LOL.
Looks nice!
Hello, sorry for the question. Why is important to use VAE for this model?
it is patch model which is trained to fix faces eyes and other ,after 1.5 sd model
Think of VAE as a patch that improves the autoencoder for the original stability diffusion codebase. In short, it makes slight improvements to a subjects anatomy which makes for more realistic image generations.
The next version of VisionGen (v1.2) will contain a baked-in VAE (vae-ft-mse-840000-ema-pruned). Although I'm hesitant to remove the VAE requirement until I've seen conclusive results on how models with/without VAE injections compare. I'm actually doing these tests for the next version of this model and another model I've recently released. As of now, VAE is still required.
@chethancheethak122聽 thank you 馃檹
@ndimensional thank you for the explanation. I understand now. I have some issues to know how to install VAE. In general have amazing results 馃憣.
Looking forward for this new version 馃榾
This model rocksssss
Do we need to activate the VAE in settings? or by placing in VAE folder its done automatically?
In the webui settings tab, there should be a setting to select VAE.
Im still new and dont know how to use VAE files, as another author told me do we have to rename the vae file to mirror the model name in this case "visiongenRealism_visiongenV10.vae.pt"
Thank you
great model! looking forward to the custom inpainting models for holding objects, firearms etc.
would you possibly look into a model trained on musicians im trying to gererate people holding a guitar and just dosent work!
or a lora to mix in with your models for female holding guitar, and or microphone
In your Steps example sheet, are those the 4 most Samplers you recommend for visionGen, or just random?
Thank you!
Those are the four Samplers that I use most often, as a result they're the four main samplers I test when creating a model. Feel free to experiment with other samplers, you might find some interesting results!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.