Babes

📲 Commissions, Training, Consultation - Flux, Pony, SDXL + Characters, Styles, Faces + ❤️ Support 🫶 Discord
❓ Poll: Which version of Babes you would like to use with Civitai generator?
ℹ️ Babes 1.21 Pony - Changes to the base style of Babes 1.2, intended to offer additional complementary options.
ℹ️ Babes 1.2 Pony - Finetuning based on Babes Kissable Lips 3.4.
ℹ️ Babes 3.1 includes new training, a new recipe, rebalanced styles, and enhancements to the base style.
ℹ️ Babes 3.0 was trained with 43,000 images, including many new styles and subjects.
ℹ️ Styles: Babes 1.1 - "basety style", Babes 2 - "abbe bi style", Sassy Girls - "sassy style", Midjourney - "midjourney style".
ℹ️ Cartoon styles:

othalama style, ronidu style, seviechan style, samdoesart style, thepit style, owler style, cherrmous style, arosen style, uodenim style, stanleylau style, amime style

ℹ️ Enhanced faces:

Jennifer Lawrence, Emma Stone, Emma Watson, Hayley Williams, Lady Gaga, Lana Del Rey, Taylor Swift, Emilia Clarke, Sophie Turner, Charlize Theron, Natalie Portman, Emily Ratajkowski, Gal Gadot, Sienna Miller, Nina Dobrev, Audra Miller

ℹ️ Recommended tags in the negative prompt: nose stud, piercing
ℹ️ Misc trigger words: wild nature, suicidegirl, interior design, digital art
ℹ️ Photography styles:

aleksei gilev style, andrew vasiliev style, elenok ella style, ivan kovalev style, jack metthey style, jiri tulach style, komrant style, marie dashkova style, mewel style, olga boyko style

ℹ️ Subjects that might have improved:

marina visconti(329), gianna michaels(254), ivy lebelle(245), hannah hays(219), darcie dolce(213), riley reid(200), riley star(200), alex coal(200), violet starr(199), tiffany watson(196), christy marks(196), avi love(192), skylar vox(192), little caprice(190), brandi bae(178), lana rhoades(178), faye reagan(174), krystal boyd(167), foxy alissa(113), emily addison(99), alissa foxy(84), lucie wilde(72), katerina hartlova(58), lara brookes(58), mila azul(57), alison tyler(55), angel wicky(52), september carrino(48), micky bells(42), lena paul(41), kennedy leigh(41), emily bloom(40), colleen a(39), yenn cat(38), jade jantzen(37), ines cudna(37), nicolette shea(36), codi vore(36), tahlia paris(35), barbie kelley(33), kym graham(32), caprice a(27), katherine a(23), elsa jean(21), aria giovanni(21), sindy(21), amelie lou(21), hiromi(21), sally charles(21), sofy b(21), august taylor(21), iveta c(21), clelia(21), bella gray(21), lucy vixen(21), carinela(21), jane w(21), hazel grace(21), cuntree pipes(21), maserati(21), kaisa nord(21), uma(21), alex legend(21), tarra white(21), angela white(21), lorena b(21), xena(21), koni demiko(21), cassidy banks(21), olga w(21), carol(21), muna(21), sophie dee(21), ian scott(21), aj applegate(21), dominika jule(21), benita(21), kay j(21), zofeya(21), olya n(21), kristy az(21), oiled(21), kagney lynn karter(21), clarke kent(21), delzangel(21), tali dova(21), courtney simpson(21), danni rivers(21), lola(21), nikki rhodes(21), missy mae(21), foxy salt(21), schoolgirl(21), michelle bond(21), karin spolnikova(21), anita(21), dominika a(21), elena(21), luna star(21), olivia(20), natalia b(20), lada(20), jordan ash(20), angelica a(20), amber b(20), vicky b(20), autumn jade(20), bill bailey(20), goldie a(20), paris jade(20), melody marks(20), payton preslee(20), mila amour(20), kim(20), ava addams(20), holly halston(20), emily willis(20), pavla(20), ava dalush(20), codi bryant(20), eva notty(20), dakota(20), linnda(20), eiby shine(20), alura jenson(20), hilary c(20), lily madison(20), raylene richards(20), inga zolva(20), daisy stone(20), amateur(20), danielle trixie(20), eva shanti(20), rinna ly(18), alaya(18), penelope b(18), bella spark(18), nikia a(18), valencia(18), cadence carter(17), carlie christine(17), bree daniels(17), adriana chechik(17), amber grand(17), lana rhodes(16), melanie jane(16), rita rush(16), bailey(16), rachel aldana(16), dolly fox(16), lana kendrick(16), jordan carver(16), molly evans(16), nika nikola(16), leanne crow(16), mandy dee(16), maggie green(16), elektra rose(16), stef(16), amber alena(16), gigi sweets(16), katya clover(16), merilyn sakova(16), mia khalifa(16), evelyn payne(16), promise(16), kelly madison(16), victoria vale(16), addison miller(16), nick strokes(16), holly garner(16), delia rose(16), ami jordan(16), li moon(16), denise milani(16), maxa(16), carolina sweets(16), luna amor(16), alexsis faye(16), nika a(16), aubrey addison(16), lisa ann(16), maggie bliss(16), gabbie carter(15), lana lea(15), big tits(15), jana mrazkova(15), sophie may(15), teen(15), amy leigh andrews(15), chloe lamour(15), faye regan(14), cherry jul(14), lucia maria(14), sabrina maree(14), sapphira(13), buffy(13), katie fey(12), vanda b(12), tessa fowler(12), stacey poole(12), lovely lilith(12), chanel fenn(10), faye valentine(9), gianna rossi(8), dylann vox(8), darcie dolche(6)

📌 Are your results not 100% identical to any specific picture?

1. Make sure to use Hires-fix from example SwinIR_4x / 4x-UltraSharp / 4x-AnimeSharp / RealESRGAN_x4plus_anime_6B (Upscaler Download), it is what I usually use for hires-fix.

2. Use VAE: vae-ft-mse-840000-ema-pruned for better colors. Download it into "stable-diffusion-webui/models/VAE" folder. Select it in the settings.

3. I use xformers - it's a small performance improvement that might change the results. It is not a must to have and can be hard to install. Can be enabled with a command argument "--xformers" when launching WebUI.

4. WebUI is updated constantly with some changes that influence image generation. Many times technological progress is prioritized over backward compatibility.

5. Hardware differences may influence changes. I've heard that a bunch of people tested the same prompt with the same settings, and the results weren't identical.

6. I have seen on my own system, that when running as part of a batch, may change a little bit the results.

7. I suspect there are hidden variables inside modules we can't change that produce slightly different results due to internal state changes.

8. Any change in image dimension, steps, sampler, prompt, and many other things, can cause small or huge differences in results.

📌 Do you really want to get the exact result from the image? There are a few things that you can do, and possibly get even better results.

1. Make a single word changes to prompt/negative prompt and test, and push it slowly to your desired direction.

2. If the image has too much of something or doesn't have enough of something, try to use emphasis. For example, too glossy? use "(glossy:0.8)", or less, or remove it from the prompt, or add it to the negative. Want more, use values 1.1-1.4, then additional descriptors in the same direction.

3. Use variations - use the same seed, and to the right of the seed check "Extra". Set "Variation strength" to a low value of 0.05, generate a few images, and watch how big the changes are. Increase if you want more changes, and reduce if you want fewer changes. That way you can generate a huge amount of images that are very similar to the original, but some of them will be even better.

📌 Recommendations to improve your results:

1. Use VAE for better colors and details. You can use VAE that comes with the model or download "vae-ft-mse-840000-ema-pruned from (https://huggingface.co/stabilityai/sd-vae-ft-mse-original/tree/main) , ckpt or safetensors file into "stable-diffusion-webui/models/VAE" folder. In the settings find "SD VAE", refresh it, and select "vae-ft-mse-840000-ema-pruned"(or the version included with the model). Click "Apply settings" button on the top. The VAE that comes with the model is "vae-ft-mse-840000-ema-pruned", you don't need both, use the one that you downloaded, it will work very well with most of the other models too.

2. Use hires-fix, SwinIR_4x / 4x-UltraSharp / 4x-AnimeSharp / RealESRGAN_x4plus_anime_6B (Upscaler Download), first pass around 512x512, second above 960x960, and keep the ratio between the two passes the same if possible.

3. Use negatives, but not too much. Add them when you see something you don't like.

4. Use CFG 7.5 or lower, with heavy prompts, that use many emphases and are long, you can go as low as 3.5. And generally try to minimize the usage of emphasis, you can just put the more important things at the begging of the prompt. If everything is important, just don't use emphasis at all.

5. Make changes cautiously, changes made at the beginning of the prompt have more influence. So every concept can throw your results drastically.

6. Read and use the manual (https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features).

7. Learn from others, copy prompts from images that look good, and play with them.

8. DPM++ 2M Karras is the sampler of choice for many people, including me. 40 steps are plenty, and I usually use 20.

9. Discord server for help, sharing, show-offs, experiments, and challenges