dreamdrop / README.md
ehristoforu's picture
Update README.md
4b9bb6f
|
raw
history blame
1.71 kB
metadata
license: other
license_name: dreamdrop-license
library_name: diffusers
pipeline_tag: text-to-image
instance_prompt: >-
  epic realistic, faded, ((neutral colors)), art, (hdr:1.5), (muted colors:1.2),
  pastel, hyperdetailed, (artstation:1.5), warm lights, dramatic light,
  (intricate details:1.2), vignette, complex background, rutkowski
inference:
  parameters:
    negative_prompt: >-
      (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong
      anatomy, extra limb, missing limb, floating limbs, (mutated hands and
      fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting,
      blurry, amputation
    num_inference_steps: 22
    guidance_scale: 8
    width: 512
    height: 512

DreamDrop V1

preview

This is a new modern model trained on Deliberate V5 with LoRA - MJLora.

Optimal settings in Automatic1111:

steps - 20-22;

cfg scale - 7-8;

sampler - DPM++ 2M Karras/UniPC;

optimal negative prompt - (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly , disgusting, blurry, amputation;

addition to the prompt - epic realistic, faded, ((neutral colors)), art, (hdr:1.5), (muted colors:1.2), pastel, hyperdetailed, (artstation:1.5), warm lights, dramatic light, (intricate details:1.2), vignette, complex background, rutkowski;

Use and improve, there are many versions of the model in the Files tab!