Forum: Poser 13


Subject: POSER to AI - OMG !

qaz opened this issue on Jan 15, 2024 ยท 56 posts


shvrdavid posted Tue, 30 January 2024 at 6:00 PM

Poser to Stable diffusion (run locally). 

I used Poser to do the openpose poses, and the seed images. 

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

ControlNet images from Poser, RealCartoonPixar Checkpoint, a few merged LoRa's and VAE's, Steps: 52, Sampler: DPM++ 2M Karras, CFG scale: 7

Prompts:

beautiful princess, solo:1.5, erotic, thin waist, dark hair, wavy hair, ((vibrant jewelry:1.5)), ((breast implants:1.2)), ((Black Lace bra, Black cape with sleeves)), highly detailed, (masterpiece:1.3), (best quality:1.2), (intricate detailed:1.2), (hyperrealistic:1.2), (professional photography:1.1), tempting pose near the window of a gothic bedroom with a day view,(casual:1.2), cinematic lighting,

Negative prompt: 

ugly, deformed, noisy, blurry, distorted, grainy, drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, (worst quality, low quality, normal quality, low res, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad eyes, bad photo, bad photography, bad art), (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark), (blur, blurry, grainy), morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, ((bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs,deformities:1.4)), 

The trick to this, is learning what keywords the models accept. And the results you will get from using them. Posting them for the first image, since it is in the TOS to do so.....

Some more examples. of different models, styles and prompts. And if you have a GPU that can do it locally, there are toms of resources available to do so. Prompts were very similar, but varied based on keywords used to train the models.

CivitAI is where I got most of the models, but not all of them. My gpu has 12 gig of memory, which is about the lower limit for a lot of this when run locally.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~




Some things are easy to explain, other things are not........ <- Store ->   <-Freebies->