Download
1 variant available
fp16 SafeTensor
SRO V6-B.safetensors
Half precision, best balance (pruned) • 1.99 GB
Verified: a year ago
186
1.5K
SR-Omega is a merge of a few handpicked checkpoints/mixes which aims to help generate semi-realistic images.
This was supposed to be an update to SR-Alpha, but the style of this merge's outputs was way too different to be classified as such, as, in my opinion, the images generated with this merge have drastically more realistic proportions compared to the older model.
This merge is a combination of the following models/mixes below:
V1:
V2:
V3 and V4:
V5:
I highly recommend inpainting for best results and to unlock the full potential of the merge. Separate inpainting model not required. Face restore (GFPGAN) has been used to just bring out a bit of realism to the outputs. Codeformer seems to do fine, but it interferes with the styling of the output and overpowers some of the facial details embedded in prompts too much even at balanced weights.
Recommended Settings:
Sampling Method: DPM++ 2M Karras, DPM++ 2S a Karras, or Euler A
Sampling Steps: 20-30
CFG = 7-10
Denoising Strength = 0.3-0.5 (img2img/inpainting)
*I only use denoising strength values greater than 0.4 if I want to drastically change the appearance of a particular feature/region of the image. I mainly use this if I want to fix hands that seem to be too deformed to be saved with lower denoising strength values.
Suggested Embeddings:
https://civitai.com/models/17083/bad-picture-negative-embedding-for-chilloutmix
https://cdn.discordapp.com/attachments/1032948846197747731/1069660323709190195/bad-hands-5.pt
Deep Negative V1.x - V1 75T | Stable Diffusion Textual Inversion | Civitai
Bad artist Negative embedding - Bad artist | Stable Diffusion Textual Inversion | Civitai
VAE:
Credits to the respective original creators of the resources used.