I am really enjoying the model aZovyaPhotoreal_v2 for creating sci-fi space like images.

Generating data

--

parameters

long shot scenic professional photograph of full shot, people, one woman, auburn hair, blue eyes , pilot officers, on the command bridge of a giant space ship, overlooking a nebula, robotech, crew, detailed skin texture, (blush:0.5), (goosebumps:0.5), subsurface scattering
Negative prompt: NSFW, Cleavage, Pubic Hair, Nudity, Naked, Au naturel, Watermark, Text, censored, deformed, bad anatomy, disfigured, poorly drawn face, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, disconnected head, malformed hands, long neck, mutated hands and fingers, bad hands, missing fingers, cropped, worst quality, low quality, mutation, poorly drawn, huge calf, bad hands, fused hand, missing hand, disappearing arms, disappearing thigh, disappearing calf, disappearing legs, missing fingers, fused fingers, abnormal eye proportion, Abnormal hands, abnormal legs, abnormal feet, abnormal fingers
Steps: 25, Sampler: DPM2 a Karras, CFG scale: 7, Seed: 3402089243, Face restoration: CodeFormer, Size: 768x512, Model hash: 5594efef1c, Model: aZovyaPhotoreal_v2, Denoising strength: 0.4, Hires upscale: 1.75, Hires upscaler: None, Version: v1.4.0

postprocessing

Postprocess upscale by: 3, Postprocess upscaler: Nearest, Postprocess upscaler 2: R-ESRGAN 4x+, CodeFormer visibility: 0.324, CodeFormer weight: 0.296

extras

Postprocess upscale by: 3, Postprocess upscaler: Nearest, Postprocess upscaler 2: R-ESRGAN 4x+, CodeFormer visibility: 0.324, CodeFormer weight: 0.296

  • nottheengineer@feddit.de
    1·
    1 year ago

    Does that huge negative prompt actually work? I found that I usually get better results if I keep the negative prompt shorter and turn up CFG scale to 8 or 9.

    I also found that a high CFG scale is good at showing you which prompts work together and which ones don’t. If you crank CFG scale to 15-20 (which will naturally produce some abominations) but find that it still ignores part of your prompt, change that part specifically because all it does is confuse the model.

    • mack123@kbin.socialOP
      1·
      1 year ago

      It is an interesting question. I am not sure. The style is from a YouTube channel I followed to learn about automatic1111.

      I included the expanded version of the style for duplication purposes. I get better results with it on and the sfw style certainly keeps the model behaved.

      I have also had very good results without it. It seems that just casting a wide with a few batches will yield at least one or two useful images, regardless of using the styles.

      I am still learning… Very early days.