icon-logo
Dark Sun
Checkpoint
coll-num35
look-num5048

7b

18+
share
selectCommunity
Model Permissions:
prompt-imgEveryone Can See The Model
prompt-imgAnyone Can Use The Model
prompt-imgCommercial Use Prohibited
D
DrDugong
uploader
Details
Category
BASE MODEL
Type
Checkpoint-Merge
Base Model
SD 1.5
Support
ControlNet | I2I/T2I
Uploaded
January 16.2024
Added
35
Runs
5048
Security
Verified

My models are just a mix of everything that you yourself can find on this wonderful site. I'm not chasing fame, I don't need your money, I just sometimes spend a few hours of my free time experimenting with my favorite models. The page with this model exists on this site only because once my friends asked me to share their mix. And because it's just damn convenient. Please don't accuse me of stealing someone's property. Considering what we're all doing here, that's a little ironic. In my mixes, I use such checkpoints as Luma, RevAnim, DDosmix, Perfect World, GalenaRedux, DarkSushi, CosmicBabes and so on. I don't even remember all the model names. I don't do anything that you can't do yourself.

Try, experiment, enjoy!

Here is the workflow for my pictures:

  1. Sampler: DPM++ 2M Karras (because it runs faster on my weaker hardware, while giving a good result)
  2. Base image size: 512x768 (because I don't have enough VRAM for more).
  3. CFG Scale - 7. Steps - 30.
  4. Default negative line: EasyNegative, drawn by bad-artist, sketch by bad-artist-anime, (bad_prompt:0.8), (artist name, signature, watermark:1.4), (ugly:1.2), (worst quality, poor details:1.4), bad-hands-5, badhandv4, blurry, child, loli, kids

Then I generate 5 pictures to identify any obvious problems, after that I make another 10-20 pictures, choose the best one from them and proceed to the upscaling stage.


  1. I turn on the option Hires.fix
  2. Upscale by - 2 (because I don't have enough VRAM for more)
  3. Upscaler - 4xUltraSharp
  4. Haires steps - 15 (half of the steps from the first stage)
  5. Denoising strength - from 0.3 to 0.6 (the larger this value, the more detailed the picture will be, but the greater the risk of getting artifacts and distortions in those places that the neural network considers doubtful or incomprehensible)
  6. Turn on ADetailer. The 1st is - face_yolov8.pt, the 2nd is the mediapipe_face_mesh_eyes_only. If necessary, I fill in its positive and negative lines, but more often this is simply not necessary.
  7. PROFIT!


Show More
Gallery