Photorealistic AI Generated Images

I find some models create a great figures based on "simple" less descriptive prompts, while others tend to be trained on more realistic body types out there, perhaps Maybe the ideal sexy figures (to me) are not as trainable, who knows. But if I use one model that creates great bodies but not necessarily great faces or other things, I create the base image in model A then upscale using model B. The results are pretty good, I think.

00001-AkibaHalloween.jpg00002-AkibaHalloween.jpg00007-AkibaHalloween.jpg00009-AkibaHalloween.jpg00014-AkibaHalloween.jpg00017-AkibaHalloween.jpg00020-AkibaHalloween.jpg00021-AkibaHalloween.jpg00024-AkibaHalloween.jpg00029-AkibaHalloween.jpg00030-AkibaHalloween.jpg00033-AkibaHalloween.jpg00035-AkibaHalloween.jpg00036-AkibaHalloween.jpg00041-AkibaHalloween.jpg00043-AkibaHalloween.jpg00046-AkibaHalloween.jpg00048-AkibaHalloween.jpg00052-AkibaHalloween.jpg
 
Using Comfyui instead of Forge (or Automatic1111) produces different results due to the different technologies under their hoods. Another cool thing about Comfyui is that you can also use the Wan2.2 text to video model to generate images by simply generating 1 frame of video. And, it has the full power of the Wan2.2 model. Produces pretty nice results!

W22_00014_.jpg
 
What is the prompt to this? I have gemini pro, I want to try


between this prompt, for consistensi I just chat with "more pose" or "different pose" :

"A sensual photograph of a Southeast Asian woman posing against a plain background, with artistic lighting, ice on skin."


"A young Japanese woman poses sensually with water droplets and ice cubes, in a dramatic, cinematic style against a plain background."


"A Japanese young woman poses sensually with an ice cube on her breast, in a soft-lit, artistic style."

other prompt from chatgpt:

"Ultra-realistic portrait of an elegant young woman wearing lace lingerie, photographed in a dark minimalist studio. Soft cinematic lighting, water droplets on her skin, a melting ice cube resting near her upper chest, subtle sensual expression, fine skin texture, detailed lace fabric, moody atmosphere, three-quarter close-up composition"
 
Last edited:
  • Like
Reactions: Casshern2
Tried this prompt with some changes because overall that's a great image it produces! Came out nice I think. Thanks for sharing! I used Forge with wildcards in the prompt, forgetting all the names I had in the name file were Japanese LOL. But, Southeast Asian can threw more because of the weight I suppose.

Wildcard prompt: "POV, Ultra-realistic portrait of an elegant, older (Southeast Asian:1.6) woman, __name__, soft skin, high cheek bones, thin face shape, wet hair, wearing sheer lace __colors__ lingerie, soft nipples, photographed in a dark minimalist studio. Soft cinematic lighting, water droplets on her skin, she holds an ice cube to her chest, the ice cube it touching her chest, subtle sensual expression, fine skin texture, detailed lace fabric, moody atmosphere, three-quarter close-up composition"


Positive prompt: POV, Ultra-realistic portrait of an elegant, older (Southeast Asian:1.6) woman, Saiko Yatsuhashi, soft skin, high cheek bones, thin face shape, wet hair, wearing sheer lace lime green lingerie, soft nipples, photographed in a dark minimalist studio. Soft cinematic lighting, water droplets on her skin, she holds an ice cube to her chest, the ice cube it touching her chest, subtle sensual expression, fine skin texture, detailed lace fabric, moody atmosphere, three-quarter close-up composition

Negative prompt: splash, dripping

Steps: 6, Sampler: LCM, Schedule type: Karras, CFG scale: 1.1, Seed: 322066404, 1024x1024, Model: gonzalomoXLFluxPony_v40UnityXLDMD, Clip skip: 2

02316-322066404.jpg
 
  • Like
Reactions: jcjc