SD3Medium Realisitc Photo

This is my first SD3 attempt with ComfyUI

Metadata:

1. Checkpoint SD3 Medium

2. Prompt

• Default: masterpiece, best quality, ultra realistic, raw photo, award-winning photography, high resolution, professional portrait photography

• Positive Prompt - Clip: the prompt that will be processed by Clip_L and Clip_G

• Positive Prompt - t5xxl: the prompt that will be processed by t5xxl

• Negative prompt (by default): 2d, 3d, unreal, animate, cartoon, anime, cg, manga, bad anatomy, bad hands, three hands, three legs, bad arms, missing legs, missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, extra eyes, 2girl, amputation, disconnected limbs, fused legs,

3. Output Format: 768 * 1152 (the portrait format)

4. Steps: 25

5. sampler: dpmpp_2m

6. scheduler: sgm_uniform

No Hires Fix, which will be included later

**** 2024.06.22 ****

• An Hires Fix is added

  • Steps Basic: number of diffusion steps for the basic image

  • Steps Hires: number of diffusion steps for the Hires Fix

    • Output Format: 1000 * 1500 (the portrait format)

    • Denoise Hires Fix: denoise factor for the enlarged image

    • Positive Prompt - Clip (default/background): masterpiece, best quality, ultra realistic, raw photo, award-winning photography, high resolution, professional portrait photography

**** 2024.08.11 ****

The Previous Positive Prompt - Clip is now renamed as SDXL Prompt. Because clip_l and clip_g are the CLIPS used in SDXL and acting as the `translator` between text and image. So I think this is the main place where you can place your prompt. The prompt are separated into three parts so have a better control over the content.

Random seed control will be added in the next version.