Model Information





Description
Check out Edge Of Realism, my new model aimed for photorealistic portraits!
"Instruct" LoRA coming soon! Will generate decent images from single line prompts, no negatives needed! Example below!
Prompt: bunny on dirt path at night, dramatic lighting, <lora:Level4_Generation:0.2>
Requires a good deal of prompt crafting. I would recommend finding a prompt that generates the style and quality to your liking and saving it as a style. Working on improving the model and training an Instruct LoRA.
I use vae-ft-mse-840000-ema-pruned with this model.
I don't remember all the merges I made to create this model. I have it recorded somewhere. Enjoy!
!!!WARNING!!!
This model is meant for SFW content, however it seems to excel and lean towards NSFW content. Was going for a hyper realistic general purpose model. Merged with a lot of different models.
Level4
15.3Kdownloads
Download ModelModel Details
- Type
- AI Model
- Task
- text-to-image
- Subtype
- Safetensors / Checkpoint AI Model
- Created
- Updated
- June 7, 2026