Create sexy art using VaM + Stable Diffusion

Guides Create sexy art using VaM + Stable Diffusion

Overview Updates (2) Reviews (9) Discussion
Just put the models in the "models" directory. And then refresh your browser. You can then select them in the GUI of Stable Diffusion!
 
pinosante said:
Just put the models in the "models" directory. And then refresh your browser. You can then select them in the GUI of Stable Diffusion!
Click to expand...
Thank you. Is it just the one file or do you need another? I saw someone mention a VAE file.
 
Some files have a VAE. The Anythingv3 file has a VAE file, you need to put that in models/vae. The .ckpt file needs to be in models/stable-diffusion. For HassanBlend1.4 there is no VAE file, so I put the HassanBlend1.4.ckpt in the models/stable-diffusion directory.
 
a cool trick to get it to do more of what you want is to give it some color beforehand and steer it in the right direction afterwards
this is what I did for a post on patreon:
juno cca.jpg

to get it to do colors like that just with prompts is impossible and to photoshop it later would take forever.
what I did to steer it in the direction I wanted was this:
!junotest.jpg

added a bit of color to the original and a big black blob and told the AI it's a smartphone

this is gonna be wild for fashion design!
 
SPQR said:
a cool trick to get it to do more of what you want is to give it some color beforehand and steer it in the right direction afterwards
this is what I did for a post on patreon:
View attachment 185973
to get it to do colors like that just with prompts is impossible and to photoshop it later would take forever.
what I did to steer it in the direction I wanted was this:
View attachment 185974
added a bit of color to the original and a big black blob and told the AI it's a smartphone

this is gonna be wild for fashion design!
Click to expand...
That’s smart! Could you share your prompt with this one? And models?
 
SPQR said:
a cool trick to get it to do more of what you want is to give it some color beforehand and steer it in the right direction afterwards
this is what I did for a post on patreon:

to get it to do colors like that just with prompts is impossible and to photoshop it later would take forever.
what I did to steer it in the direction I wanted was this:

added a bit of color to the original and a big black blob and told the AI it's a smartphone

this is gonna be wild for fashion design!
Click to expand...

That's what i'm doing too, helps a lot!
 
pinosante said:
That’s smart! Could you share your prompt with this one? And models?
Click to expand...

i don't have the original settings anymore, it's an old image. but they were not that good, redid it just now.
you can copy it and hit "paste image settings" in SD UI. you'll also need to add the input image above

Code: 
{"numOutputsTotal":20,"seed":6003092,"reqBody":{"prompt":"((photograph)) of a 25 years old woman, beautiful european model, looking away,  (((((holding a blue globe sphere))))) in hand, wet hair, pale, slick back brunette hair, (brown eyes),  wearing a white wet transparent gown toga with red wet shawl, gold crown, surprised, ((taking a selfie)) with (phone), (((gray wall background))), (photorealistic),smooth, glowing, fluorescent, sharp focus,  ultra detailed, realistic , hyper realistic, low angle,","negative_prompt":"blurry, art, (painting:2), rendering, drawing, sketch,anime, cartoon, fake, drawing, illustration, boring, 3d render, long neck, out of frame, extra fingers, mutated hands, ((monochrome)), ((poorly drawn hands)),  cgstation, red eyes, multiple subjects, extra heads, close up, man, child, children, kids childlike, doll, text ,watermarks, logo, airbrush, amputee, anime, anime eyes, anorexic, bad anatomy, bad eyes, bad proportions, bad proportions , blind, blur, blurry, blurry, cartoon, censored, character design, cloned face, closeup, closeup, cropped, cropped, cross eyed, day, dead eyes, deformed, disfigured, duplicate, error, extra arms, extra fingers, extra legs, extra limbs, fake, fused fingers, gaussian, grainy, gross proportions, high pass filter, jpeg artifacts, logo, long neck, low quality, low quality, lowres, malformed limbs, missing arms, missing legs, monochrome, morbid, morning, mutated, mutated hands, mutation, mutilated, noisy, normal quality, obese, out of focus, out of frame, out of shot, over saturation, over shadow, overlay, oversaturation , painting, polygons, poorly drawn face, poorly drawn hands,  rendering, screenshot, signature, software, text, text, titles, too many fingers, twitter ui, ugly, ugly eyes, ui, username, vignette, watermark, watermark, wireframe, words, worst quality, worst quality, worst quality, writing, zoomed, (((((food))))),birds, disney,","active_tags":[],"width":448,"height":1024,"seed":6003092,"num_inference_steps":50,"guidance_scale":25,"prompt_strength":0.63,"use_face_correction":true,"sampler":"ddim","use_stable_diffusion_model":"HassanBlend1.4","use_vae_model":"vae-ft-mse-840000-ema-pruned","num_outputs":1,"stream_image_progress":false,"show_only_filtered_image":true,"output_format":"jpeg"}}

seed: 6003098
juno1.jpg
seed: 6003097
juno2.jpg
seed: 6003096
juno3.jpg
 
SPQR said:
i don't have the original settings anymore, it's an old image. but they were not that good, redid it just now.
you can copy it and hit "paste image settings" in SD UI. you'll also need to add the input image above

Code: 
{"numOutputsTotal":20,"seed":6003092,"reqBody":{"prompt":"((photograph)) of a 25 years old woman, beautiful european model, looking away,  (((((holding a blue globe sphere))))) in hand, wet hair, pale, slick back brunette hair, (brown eyes),  wearing a white wet transparent gown toga with red wet shawl, gold crown, surprised, ((taking a selfie)) with (phone), (((gray wall background))), (photorealistic),smooth, glowing, fluorescent, sharp focus,  ultra detailed, realistic , hyper realistic, low angle,","negative_prompt":"blurry, art, (painting:2), rendering, drawing, sketch,anime, cartoon, fake, drawing, illustration, boring, 3d render, long neck, out of frame, extra fingers, mutated hands, ((monochrome)), ((poorly drawn hands)),  cgstation, red eyes, multiple subjects, extra heads, close up, man, child, children, kids childlike, doll, text ,watermarks, logo, airbrush, amputee, anime, anime eyes, anorexic, bad anatomy, bad eyes, bad proportions, bad proportions , blind, blur, blurry, blurry, cartoon, censored, character design, cloned face, closeup, closeup, cropped, cropped, cross eyed, day, dead eyes, deformed, disfigured, duplicate, error, extra arms, extra fingers, extra legs, extra limbs, fake, fused fingers, gaussian, grainy, gross proportions, high pass filter, jpeg artifacts, logo, long neck, low quality, low quality, lowres, malformed limbs, missing arms, missing legs, monochrome, morbid, morning, mutated, mutated hands, mutation, mutilated, noisy, normal quality, obese, out of focus, out of frame, out of shot, over saturation, over shadow, overlay, oversaturation , painting, polygons, poorly drawn face, poorly drawn hands,  rendering, screenshot, signature, software, text, text, titles, too many fingers, twitter ui, ugly, ugly eyes, ui, username, vignette, watermark, watermark, wireframe, words, worst quality, worst quality, worst quality, writing, zoomed, (((((food))))),birds, disney,","active_tags":[],"width":448,"height":1024,"seed":6003092,"num_inference_steps":50,"guidance_scale":25,"prompt_strength":0.63,"use_face_correction":true,"sampler":"ddim","use_stable_diffusion_model":"HassanBlend1.4","use_vae_model":"vae-ft-mse-840000-ema-pruned","num_outputs":1,"stream_image_progress":false,"show_only_filtered_image":true,"output_format":"jpeg"}}

seed: 6003098
View attachment 186104		seed: 6003097
View attachment 186105		seed: 6003096
View attachment 186106
Click to expand...
This helped, thanks!
 
SPQR said:
i don't have the original settings anymore, it's an old image. but they were not that good, redid it just now.
you can copy it and hit "paste image settings" in SD UI. you'll also need to add the input image above

Code: 
{"numOutputsTotal":20,"seed":6003092,"reqBody":{"prompt":"((photograph)) of a 25 years old woman, beautiful european model, looking away,  (((((holding a blue globe sphere))))) in hand, wet hair, pale, slick back brunette hair, (brown eyes),  wearing a white wet transparent gown toga with red wet shawl, gold crown, surprised, ((taking a selfie)) with (phone), (((gray wall background))), (photorealistic),smooth, glowing, fluorescent, sharp focus,  ultra detailed, realistic , hyper realistic, low angle,","negative_prompt":"blurry, art, (painting:2), rendering, drawing, sketch,anime, cartoon, fake, drawing, illustration, boring, 3d render, long neck, out of frame, extra fingers, mutated hands, ((monochrome)), ((poorly drawn hands)),  cgstation, red eyes, multiple subjects, extra heads, close up, man, child, children, kids childlike, doll, text ,watermarks, logo, airbrush, amputee, anime, anime eyes, anorexic, bad anatomy, bad eyes, bad proportions, bad proportions , blind, blur, blurry, blurry, cartoon, censored, character design, cloned face, closeup, closeup, cropped, cropped, cross eyed, day, dead eyes, deformed, disfigured, duplicate, error, extra arms, extra fingers, extra legs, extra limbs, fake, fused fingers, gaussian, grainy, gross proportions, high pass filter, jpeg artifacts, logo, long neck, low quality, low quality, lowres, malformed limbs, missing arms, missing legs, monochrome, morbid, morning, mutated, mutated hands, mutation, mutilated, noisy, normal quality, obese, out of focus, out of frame, out of shot, over saturation, over shadow, overlay, oversaturation , painting, polygons, poorly drawn face, poorly drawn hands,  rendering, screenshot, signature, software, text, text, titles, too many fingers, twitter ui, ugly, ugly eyes, ui, username, vignette, watermark, watermark, wireframe, words, worst quality, worst quality, worst quality, writing, zoomed, (((((food))))),birds, disney,","active_tags":[],"width":448,"height":1024,"seed":6003092,"num_inference_steps":50,"guidance_scale":25,"prompt_strength":0.63,"use_face_correction":true,"sampler":"ddim","use_stable_diffusion_model":"HassanBlend1.4","use_vae_model":"vae-ft-mse-840000-ema-pruned","num_outputs":1,"stream_image_progress":false,"show_only_filtered_image":true,"output_format":"jpeg"}}

seed: 6003098
View attachment 186104		seed: 6003097
View attachment 186105		seed: 6003096
View attachment 186106
Click to expand...
What "model" are you using for those? The Hassan one?
 
this technique works really well for adding clothes

bra.jpg
tshirt.jpg

!pag.jpg


does Automatic1111 have in UI drawing? i'm using stable diffusion UI
 
What a great idea with a neural network!!! I have just launched SD on my computer for the first time. Incredible.
 
hello! very nice your tutorial! but is there any tutorial for laymen, how to install, how to configure, necessary programs?
 
Cgomes said:
hello! very nice your tutorial! but is there any tutorial for laymen, how to install, how to configure, necessary programs?
Click to expand...

If you open the Automatic1111 link at the start of the guide, and scroll down, you can find a small 4 steps guide to install stable diffusion. If it's still too obscure, search for a tutorial on youtube on how to install automatic1111! i'm sure you can find mutliple!
 
JaxZoa said:
If you open the Automatic1111 link at the start of the guide, and scroll down, you can find a small 4 steps guide to install stable diffusion. If it's still too obscure, search for a tutorial on youtube on how to install automatic1111! i'm sure you can find mutliple!
Click to expand...
Thanks!!
 
You must log in or register to reply here.

Similar threads

VirtaArtieMitchel
Clothing Stable Diffusion Graphic Tee
Replies
0
Views
502
VirtaArtieMitchel
VirtaArtieMitchel
B
Guides Using VaM to create a 3D avatar for AI running through SillyTavern
Replies
1
Views
394
bot1789
B
Hexenv88
Assets 3 Stall Stable
Replies
0
Views
406
Hexenv88
Hexenv88
TEK
Looks Art
Replies
1
Views
310
TEK
TEK
YameteOuji
Guides VAM - Using Clothing for Beginners
Replies
2
Views
583
dadirector
D
Back
Top Bottom