A Block merge with
https://civitai.com/models/125492?modelVersionId=1074417 - by HaydenHoosk
Probably my last version of Lush Synth just thought i'd finish it off with a even more real/semi real version
This is a very tenative pass at a more semi real version. Not going to pretend that is was some super complicated process, it's just a block merge with a photorealistic model, specifically:
https://civitai.com/models/153568/real-dream - by sinatra
Prompting
For the most part prompting remains the same as other versions, however, prompting for "realistic" or "photorealistic" should now push the model a lot more in that direction, the latter can desaturate the image a fair bit though. Also of note is the model likes to stick people in the background a bit more, adding "people" in the negative prompt fixed this a lot of the time in my testing
Settings
Recommended settings remain the same being:
Sampler: Euler A
Steps: 25-35
Cfg: 6-8
Increased overall saturation
Decreased the need for prompts like "glowing", "glow", "neon", ect however using them will still increase the effect
Merged in a couple of loras:
https://civitai.com/models/399825/saturation-tweaker - by oritatami_neko
https://civitai.com/models/310235/glowneon-xl-lora - by Cybernella
Increased glow and contrast capabilities
Block merge of a small amount of the middle and output blocks of https://civitai.com/models/686122/petuniafireflyxl by ConsistentFactor444
v1.1 Prompting
Words like "glow", "neon", "silhouette" should get the best results
My second block merge, this time focused on a vibrant toon/anime style.
Biggest Strength: Creates decent retro vaporwave images imo.
Biggest Weakness: Appears to have lost some abilty to generate high quality hands and faces (I hope to try and fix this but no promises)
https://civitai.com/models/898564/master-of-none - by Me
https://civitai.com/models/911243?modelVersionId=1022216 - by Vauxz
https://civitai.com/models/894950/the-p-wondermix - Lorim
https://civitai.com/models/807271/h4n4-pony-semi-real-versatile-base-model - by H4N4
https://civitai.com/models/376450/duchaiten-pony-xl-no-score - by DucHaiten
Just normal pony v6 prompting practices. (score)
Words like: "Vaporwave", "neon", "glow" have the best effect in this model
I use the following settings, but experimentation is encouraged.
Sampler: Euler A
Steps: 25-35
Cfg: 6-8
Lush Synth is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user PlaceDown. Derived from the powerful Stable Diffusion (Pony) model, Lush Synth 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 Lush Synth is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, style, toon.
With a rating of 0 and over 0 ratings, Lush Synth is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of Lush Synth from here.
To use Lush Synth, 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 Lush Synth, check out our crash course in AI image generation.
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.