Details
Ralated
Refined v11
Refined v11 Dark
Refined_v10
Refined_v10-fp16
Refined-inpainting
Refined

Refined

10.0K
965
4.5K
#Character
#person
#Photorealistic
#????
#Female
#???????
#Cyberpunk
#ckpt
#steampunk
#woman
#Fantasy
#girls
#Photography
#photorealism
#portraits
#Realism
#Character
#GIRL
#person
#Photorealistic
#????
#????
#Female
#???????
#Cyberpunk
#safetensor
#ckpt
#steampunk
#Style
#woman
#Fantasy
#girls
#Photography
#photorealism
#portraits
#Realism

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

Merged Model with slight fine-tuning focused on human ??????? and skin texture, can also be used as a general purpose model. v10 is a foundation that will be further built upon with more mergers + fine-tuning.

List of models used in merge can be found in the version description.

Limitations (as of now)

  • Photos of Men

  • Anime

  • SFW generations without specific tags

Trigger Words

Trigger words are not required.

However, the following tags can be used to alter the generation.

analog style, modelshoot style, wa-vy style, synthwave, sci-fi, cyborgdiffusion, ????? ?????, flaccid ?????, postapocalypse, 3d, render, ????, sfw

For tags like "????", "sfw", "3d", and "render", you can swap these between your positive and negative prompts to get more specific outputs.

For example, putting "sfw" in your positive prompt, and "nsfw" in your negative prompte will push the model in the direction of generating sfw outputs. You can also add/decrease attention using ()and []

Textual Inversion (TI)

Many of sample images include a negative textual inversion that helps fix things like hands, ect.. This isn't a requirement, I've tested the model without this TI and didn't have any issues. I do recommend using it though, as it does help.

Bad Prompt TI - https://huggingface.co/datasets/Nerfgun3/bad_prompt

I recommend using Version 2 and setting it's weight to 0.8 in the negative prompt; (bad_prompt_version2:0.8)

For webui, bad_prompt_version2.pt goes in:

sd/stable-diffusion-webui/embeddings

Hires Fix

I used Hires Fix for many of the sample images. This is not a requirement but it does seem to improve results. I mainly use latent(bicubic antialiased) with Denoising strength set to 0.65.


Check out my other models

SDXL

SD1.5

LoRA

Questions or Feedback?

Visit my thread on the Unstable Diffusion Discord Server

View Translation

Rating & Review

5.0 /5
0 Ratings

Not enough ratings or reviews received yet

N
Notice
2023-03-20
Publish Model
2023-05-19
Update Model Info
Model Details
Type
Checkpoint
Publish Time
2023-05-19
Base Model
SD 1.5
Version Introduction

Refined v11

Rebuilt from the ground up.

How to use configuration file (.yaml) :

Simply drag and drop the .yaml into the same location of the model. Make sure the name matches the name of the model.

Note : To use the config file with the fp16 version of the model. The config must be renamed to match the name of the model.

So, Refined_v11-fp16.safetensors config would be Refined_v11-fp16.yaml

What's included :

  • Refined_v11.safetensors | Full model | FP32 | Safetensors

  • Refined_v11.yaml | Config

  • Refined_v11-fp16 | Pruned model | FP16 | Safetensors

  • Refined_v11.ckpt | Full model | FP16 | PyTorch (.ckpt)

License Scope
Model Source: civitai

1. The rights to reposted models belong to original creators.

2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim

Creative License Scope
Online Image Generation
Merge
Allow Downloads
Commercial License Scope
Sale or Commercial Use of Generated Images
Resale of Models or Their Sale After Merging
QR Code
Download SeaArt App
Continue your AI creation journey on mobile devices