Get Big Love Eryn1, Ultra5, Photo6, Zuna1 or Zia1 for $5.50 and Gwen1 or Hyper1 for $10 on Fanvue. Click 'Follow', buy a post, check your Fanvue DMs! You can get Klein2 for $10 on Tensor Art. A subscription includes the latest release and new ones within 30 days.
To create up to 85 free images per day in highest quality you can use Big Love here. For discussing photorealistic image generation join me on Discord.
Big Love Gwen is a finetune of Qwen Edit 2511 and can do NSFW image editing. It produces more realistic and sharp images with better skin texture & genitals than other Qwen checkpoints/loras. Txt2img is less reliable, but generates nice results too.
Big Love Gwen1 allows commercial usage without additional fees (if no auto-generation involved) unlike Big Love Klein. With its better anatomy it is easier to get good editing results. As fast at 6 steps as Klein at 4 steps.
The fp8 mixed version is for 16+ GB VRAM (highest quality), the nf4 version is for 12 and 16 GB VRAM (25% faster), the GGUF Q5_K_M version is for 16 GB VRAM (softest) and the nvfp4 version requires 24+ GB VRAM (on RTX 5090 2-3x faster, otherwise 2x slower, lower quality than fp8 mixed, less saturation, textured).
It is recommended to use ComfyUI. The Gwen1 workflows offer a skin enhance feature that is not available in Forge Neo. Move the Gwen1 model file into the diffusion_model sub folder of the models folder of ComfyUI, qwen_2.5_vl_7b_fp8_scaled.safetensors into the text_encoder sub folder and qwen_image_vae.safetensors into the vae sub folder.
For training a lora read here for Gwen1.
Settings are 6 steps (3 steps for upscaling), cfg1, Euler sampler, Beta scheduler, 832x1216 or 1024x1536 pixels.
Big Love Eryn is a fine-tune of Ernie-Image(-Turbo). You can run it locally with ComfyUI and Forge Neo. The fp8 version works with 8 & 12 GB VRAM. Use the (pruned) bf16 version if you have 16 GB VRAM or more. The "Full" versions are only meant for training a lora (coming soon!). Put the downloaded model into the diffusion models sub folder of ComfyUI or the StableDiffusion sub folder of Forge Neo. You additionally need to place ministral-3-3b.safetensors in the text_encoder sub folder and flux2-vae.safetensors in the VAE sub folder.
Settings are 4-6 steps (3-4 steps for upscaling), cfg1, Euler sampler, Beta scheduler, 832x1216 or 1024x1536 pixels.
Big Love Hyper supports generating at image sizes of 1664x2232 (4 megapixel) and higher with SDXL. Can be easily upscaled to 9 megapixel unlike the normal low-res images. Hyper currently has not fully stable anatomy, so needs more runs. Some prompts work better than others. It produces highly detailed and life-like images close to real photos. It has a special quality that cannot be achieved by just upscaling. The Hyper versions of Big Love are pay-only and special license conditions apply (see below).
Settings are DMD2 lora with strength 1.0, LCM Exponential, 8 steps, cfg 1, clip skip 2, 1664x2432 or 1536x2240. Upscale with img2img with DMD2 lora with strength 1.0, same prompt, LCM Exponential, 1.25-1.5x, 4-8 steps, cfg 1, 0.3-0.5 denoise, clip skip 2.
Big Love Klein is a fine-tune of Flux 2 klein. It can do txt2img but also edit images with prompts. Txt2img is currently experimental and requires more prompt & seed hunting. Image editing works stable. It only needs 4 steps, so is quite fast (5 sec on 5090, 15 sec on 5070). You can run it locally with ComfyUI and online on Tensor Art. Use the GGUF Version with 8 GB VRAM, the fp8 version with 12-16 GB VRAM and the (pruned) bf16 version with 24+ GB VRAM. The nvfp4 version (full nf4) renders 2-4x faster on RTx 5xxx GPUs with the latest CUDA drivers. The base version (full fp32 or full bf16) is meant for training a lora only. Put the downloaded model into the diffusion models sub folder of ComfyUI. You also need qwen_3_8b_fp8mixed.safetensors in the text_encoders sub folder (Qwen3-8B-Q5_K_M.gguf wth 8 GB VRAM) and flux2-vae.safetensors in the vae sub folder. Forge Neo is not recommended, because it currently produces too low image quality with Klein, which will hopefully change soon.
Settings are 4 steps (2 steps for upscaling), cfg1, Euler sampler, Beta scheduler, 832x1216, 1024x1536, 1280x1920 or 1536x2240 pixels
Big Love ZT, Zia or Zuna are fine-tunes of Z-Image(-Turbo) on the Big Love dataset. You can run it locally with ComfyUI and Forge Neo. The fp8 version works faster with 8 GB VRAM but produces more noise so may sometimes look more realistic, but details are not as good. Use the (pruned) bf16 version if you have 12 GB VRAM or more. The "Full" version is only meant for training a lora. Put the downloaded model into the diffusion models sub folder of ComfyUI or the StableDiffusion sub folder of Forge Neo. To make Big Love ZT/Zia/Zuna work you additionally need to place qwen3_4b.safetensors in the text_encoder sub folder and ae.saftendors in the VAE sub folder.
Settings are 8 steps, cfg1, Euler or DPM++ 2s a RF sampler, Normal or Simple or Beta scheduler, 832x1216, 1024x1536 or 1280x1920 pixels. For upscaling 8 steps, cfg1, Euler sampler, Normal or Simple or Beta scheduler, 1.5x upscale.
Big Love Ultra supports generating at image sizes of 1280x1870, 1360x1984 and higher. Can be easily upscaled to 6 megapixel unlike the normal low-res images. More photorealistic and detailed. A special quality that cannot be achieved by just upscaling. Ultra produces more details & sharpness when upscaling and detailing low-res images. The Ultra versions of Big Love are pay-only and special license conditions apply. See below.
Settings are DMD2 lora with strength 1.0, LCM Exponential, 8 steps, cfg 1, clip skip 2, 1280x1864 or 1360x1984. Upscale with img2img with DMD2 lora with strength 1.0, same prompt, LCM Exponential, 1.25-1.5x, 4-8 steps, cfg 1, lora strength 1.0, 0.3-0.5 denoise, clip skip 2.
Big Love Photo and Insta1 are finetuned versions of XL. Lust1 is a finetuned version of Lustify merged with Photo. They were trained on thousands of images and dozens of new concepts. Why they are the most realistic and versatile. For more details and prompting Photo1 read this article.
Settings are DMD2 lora with strength 1.0, LCM Exponential, 8 steps, cfg 1, clip skip 2, 832x1216 or 1024x1496. Upscale with img2img with DMD2 lora, same prompt, LCM Exponential, 1.25-1.5, 4-8 steps, cfg 1, lora strength 1.0, 0.3-0.5 denoise, clip skip 2.
Big Love XL is a combination of 5 different training branches of SDXL: original SDXL, bigASP, NatVis, Anteros and Pony. With a bit of Pony in it, some Pony loras (poses, characters) work too. It outputs a more photorealistic & creative look than the Pony versions and can also do paintings & cartoon.
Settings are DMD2 lora with strength 1.0, LCM Exponential, 8 steps, cfg 1-1.5, clip skip 2, 832x1216 or 1024x1496. Upscale with img2img with DMD2 lora, same prompt, LCM Exponential, 1.5-2x, 8-12 steps (XL1/XL2), 4-8 steps (XL2.5-XL4), cfg 1, lora strength 1.0, 0.3-0.5 denoise, clip skip 2.
Big Love Pony produces different images than both Pony & SDXL-based models. Pony tags are understood, but interpreted a bit differently. Some images lean more in the one or other direction depending on the prompt. It works with Pony loras as well as normal SDXL ones. It can turn anime/cartoon into photorealistic images in img2img. Pony3 includes a bit of Illustrious.
Settings are DMD2 lora with strength 1.0, LCM Exponential, 8 steps, cfg 1-1.5, clip skip 2, 832x1216 or 1024x1496. Upscale with img2img with DMD2 lora, same prompt, LCM Exponential, 1.5-2x, 8-12 steps, cfg 1, lora strength 1.0, 0.3-0.5 denoise, clip skip 2.
ComfyUI Workflow:
Download one of the following images and drag'n'drop it onto Comfy:
Klein, Eryn and Gwen workflows are embedded in the showcase images.
Z-Turbo/Z-Base txt2img & Upscale Workflow (recommended)
SDLX DMD2 txt2img & Upscale Workflow (recommended)
SDXL DMD2 txt2ing & Upscale for Big Love Ultra
SDXL DMD2 img2img Workflow
SDXL Lightning Workflow
Trained Concepts
Newer versions of Big Love include the concepts of older versions, e.g. Photo4 can do everything that Photo1 to Photo3 can do and more. The only exception are the Insta concepts, but they have been partially added to never versions too.
Photo6/Ultra5: ai-style, bodyscape, butt plug, candid amateur, cumshot, illustrious-style, outdoor sex, partner fingering, photoart, innie pussy, ray-style, rebellious, reflection, sensual, sexy ass, sweetheart, wedgie
Photo5/Ultra4/Hyper1: alluring, anal sex, artistic photo, artistic pinup, charming, cum portrait, cute asian, cute pinup, cute portrait, double oral, dreamy-style, face pov, fantasy pinup, fantasy-style, kai-style, lowkey, mj-style, outdoor flashing, photo art, pole dance, public indecency, public nudity, rock climbing, scify-style, sword pose, vaginal sex
Photo4/Photo4.5/Ultra2/Ultra3: 2girls kissing, acrobatic sex, average face, beautiful face, amateur pinup, anal fingering, artistic portrait, cuddling, cum swapping, doggystyle pov, even skin color, fashion photo, female masturbation, female pov, finger licking, food porn, footjob, french kiss, full nelson, funny movie, funny tongue out, insta cute, legs pov, low contrast, mirror portrait, nude pose, oral pov, orgasm face, outdoor nude, penis licking, pinup photo, pro photo, pro portrait, pussy licking, sex pov, sexy portrait, vaginal fingering, waterfall
Photo3/Lust1/Ultra1: 360 degree photo, 3d selfie, 69 position, adorable, alt beauty, anal gape, anal sex, average face, beach life, beautiful, beautiful face, candidness, cum, cute, deepthroat, dildo insertion, double exposure, enthusiastic, extreme pose, faces, fashion photo, female pov, fisting, follow me pov, girl next door, gorgeous, handjob, heroin chic, huge feet, huge hands, huge nipples, light rays, light streaks, lighting, low/mid/high contrast, lowkey/midkey/highkey, low/mid/high saturation, middle finger, motion blur, object insertion, detailed eyes, teeth, pro photo, pussy gape, real life, rooftop, round ass, sad, sexy pose, skin texture, skin tone, spread pussy, squirting, street portrait, testicle licking, testicle sucking, vaginal sex, voluminous hair, water splash
Insta1: amateur photo, fashion photo, insta selfie, pinup photo, pro photo, real life, big ass, bimbo, cute, luxurious, adorable, enthusiastic, average face, beautiful face, detailed eyes, sexy legs.
Photo2: 3d selfie, 69 position, adorable, alt beauty , amateur photo, ball licking, ball sucking, beach life, bubble butt, low/mid/high contrast, dildo insertion, double exposure, enthusiastic, extreme pose, female pov, follow me pov, forced perspective, girl next door, gorgeous, handjob, heroin chic, huge feet, huge hands, huge nipples, light rays, light streaks, lighting, middle finger, motion blur, no tan lines, object insertion, pussy gape, rooftop, sad, low/mid/high saturation, sexy pose, squirting, street portrait, water splash.
Photo1: amateur photo, pro photo, lighting, lowkey, midkey, highkey, beautiful, cute, candid, real life, average face, remarkable face, voluminous hair, skin tone, skin texture, 360 degree photo, spread pussy, deepthroat, fisting, anal gape, anal sex, vaginal sex.
Training a (character) lora
My advice is this: Take 10-30 high quality images (at least 50-100 for styles or poses), download OneTrainer, click the SDXL lora preset, choose Big Love as the base checkpoint, add your images as a concept, add tags on the Tools tab, and start training. If you train on Big Love Ultra change the training resolution to 1536 and provide 1248x1832 images.
You will only get the full Big Love quality by training on real photos or extremely photorealistic images, which is usually not the case with a fictional character. It is all about image quality and not choosing boring images. Don't add posing images to a character lora, because Big Love provides the posing later for it. Focus mainly on good portraits with a few upper and full body images. Rather fewer higher quality images than a lot of average images. Read here for traing a lora on Big Love ZT2, ZT3, Zia1, Zuna1 or Eryn1.
Fixing Anatomy
If you want to keep the seed and repair anatomical problems in an image, activate the Extra checkbox in A1111/Forge and set Variation Strength to 0.01 to 0.1. Then generate until anatomy is fine. In Comfy there are sampler nodes that support variation seed (e.g. Inspire Pack), which do the same thing. Also possible to change steps or add commas to the prompt, but I do not recommend it. Extra/Variation Seed is more powerful and convenient as it gives you endless variations with just one click. There is always a variation which looks similar or even better with great anatomy.
You don't need negative prompts for this. They are rather ineffective. You can also change the positive prompt to suppress things. Anatomy problems are also created by the prompt if you prompt contradicting poses that the model cannot combine. Better to fix the prompt first then.
Reducing Saturation, Warm Colors and Sharpness
These SDXL loras reduces the saturation and change the color temperature without reducing image quality. The lora strength defines the effect. Negative values increase saturation or add more warmth. To make an image softer use a lower strength for the DMD2 lora, e.g. 0.95, 0.9, 0.85.
Big Love Hyper/Ultra/Photo Sizes
Big Love Hyper supports these image sizes:
1664x2432 (recommend)
1536x2240
Big Love Ultra supports these image sizes:
1360x1984
1280x1872 (recommend)
Big Love Photo supports these image sizes:
1024x1496 (recommend)
832x1216
You can also use the 16:9 or 2:3 versions of these image sizes as well as landscape orientation, but the above should be more reliable.
The higher the image size, the lower the probability of good results. If you get too many problems with a higher image size, switch to the lower one. Some prompts do higher sizes fine, some do not. Do not use a lower image size than the recommended one, otherwise image quality will be lower. With higher image sizes anatomy problems occur too often.
Remove fill words and unusual tags in the prompt. They can cause a quality reduction with Big Love Ultra/Hyper as they were not trained. Shorter prompts should work better as it is less likely that bad or untrained tags are in it.
SFW Output - No Tits Please
"Is there a trick so that Big Love doesn't always generate raised shirts or visible breasts?" I get this asked so often, while it is so obvious. Big Love knows what men want so it gives it to them. Negatives don't work that well for it. So you got to speak to it in the positive prompt like you were taking to a nun. "Breasts? How dare you speak such an obscene word to me." Don't mention breasts or any of these sexy parts. Instead describe clothes a lot. Don't write down your impure thoughts. God forbid! Yeah, I know, so hard. Describe her body shape, which also implies certain tits underneath the clothes.
XL Prompting Advice
SDXL prompts & prompts from various SDXL checkpoints work with it. Pony prompts too, but they create a more photorealistic look. Natural language prompts tend to create artistic glamour images with less skin detail while normal tags do more photo-style images. Big Love XL gives individual words more attention, so you don't need to rework prompts like Big Love Pony requires sometimes.
XL1/XL2 has a tendancy towards cuteness and bright skin. If you get too much of it, remove words like cute, sweet, pale/fair skin & flash from the prompt. It also creates realistical analog photos with reduced image quality. Sometimes better to remove terms like analog or grain to increase quality. Decrease cfg to get a more natural look.
XL2.5 can sometimes get too sharp. Reduce cfg or use less steps in img2img to make images softer.
Pony Prompting Advice
Pony prompts & prompts from other checkpoints work with it. Score tags and fill words like masterpiece or perfect skin have as good as no effect usually. A negative prompt is often unnecessary unless you want to make something vanish or avoid underage, but it can also change the style of the image.
Pure booru tags and some other samplers may produce Pony style. Photographic terms or a simple prompts ensure a photo look. Sometimes it refuses to produce medium shots, portraits or close-ups unless you weigh the term heavily or remove feet, shoes, high heels, boots etc. from the prompt. wavy hair sometimes does not look so great.
If it refuses to do porn, try simplifying the prompt. If you want to do a portrait, don't describe surroundings too much. If you want to do porn, describe the action mainly and don't focus on the people or surroundings in the prompt. The largest part of the prompt should be about the main subject of the image.
If a prompt does not produce the intended image, you often only need to modify it a bit to make it work perfectly.
Using Character Loras
Big Love Pony supports Pony characters, but they look like real humans. There were some complaints about them not working, but the problem was not the model itself so far. So here are some tips:
* Try Pony as well as SDXL character loras
* Use a lora weight up to 1.5 if it does not reduce quality
* If it is a well known character, add the name in the prompt and also give it a higher weight if necessary.
* Check your negative prompt for problems. Delete it if necessary and rewrite it from scratch.
* Render a lot of images to be able to pick those with the best resemblance.
More SDXL Photorealism:
You can highly improve the images generated with this model by using img2img, upscaling, detailing etc. The SDXL Lightning lora enhances the look and constrast despite only 8 steps. Alternatively, the SDXL DMD2 lora produces a sharp, but more natural look with less contrast. Also check out the Subtle Style loras, which nicely enhance images.
Big Love License
Big Love SDXL versions are licensed under CreativeML Open RAIL++M (dated July 26, 2023), the Big Love Z-Image, Ernie & Qwen versions are licensed under Apache 2.0, and the Big Love Klein versions are licensed under the FLUX Non-Commercial License with the following additional terms:
For clarity, the following version tiers are defined:
Restricted versions: Ultra, Hyper, Klein, Zia, Zuna, Eryn, Gwen
Open versions: Pony, XL, Photo, Insta, Lust, ZT
1. You may use Big Love without crediting the creator.
2. You may sell the images that it generates.
3. You may only run the official Big Love versions of the SubtleShader account on Civitai and Tensor Art. Running it on other public or shared servers commercially (including other Civitai and Tensor Art accounts) requires a separate license or permission from the creator.
4. You may not sell this model or merges of this model.
5. You may not merge, share merges of, or share LoRA extractions incorporating Restricted versions. You may merge and share merges of Open versions.
6. When sharing the allowed merges of Open versions, as well as finetunes of them, you must apply these same additional license terms.
7. Redistribution of Restricted versions is prohibited. They may only be obtained from official sources designated by the creator.
8. All use-based restrictions of the CreativeML Open RAIL++M license apply to SDXL versions and their derivatives. All use-based restrictions of the FLUX Non-Commercial License apply to Klein versions and their derivatives.
9. Any restrictions in these additional terms may be waived only with explicit written permission from the creator.
TLDR: This is basically the same license as before (just stated more clearly), so nothing changes for the Pony, XL, Photo, Insta, Lust and ZT versions of Big Love. However, restrictions were added for Ultra, Hyper, Klein, Zia, Zuna, Eryn and Gwen versions (no merging, no redistribution). The "Share merges" condition below the license on the right hand side was only deactivated because of the restricted versions. Merging is still allowed for the open versions.
Many thanks to the creators of SDXL, Z, Flux klein, Pony, bigAsp and Lustify for making their wonderful models available. Big thanks to RaymondLuxuryYacht for allowing me to train on his fabulous images.
Description
Photo3 is the most capable and realistic Big Love version so far. Concepts work much better. Improved eyes & teeth. No insta look and less saturated than Insta1. Photo3 was retrained from scratch with 3900 images, 61 concepts and a different strategy. Old dataset improved, new images added.
FAQ
Comments (89)
This is absolutely stunning! Thank you!
Big Love Photo3 & Illustrious1
I will release Photo3 tomorrow or on Monday. The best Big Love version yet IMHO. Could not stop generating.Then I plan to train the Photo3 training set on Illustrious. Should become an interesting artistic-photorealistic checkpoint. I got more in the pipeline: Photo4, PhotoArt1 and another project that I don't want to reveal just yet.
Will the Photo3 Illustrious version be something I can use without LCM sampler?
@AFD_0 DMD2 with LCM is not mandatory but usually better.
Did some Illustrious tests, but reminds me too much of Big Love Pony3, which already has Illustrious merged in. Might try another approach if that does not work, I'll have to delay Illustrious until later.
@SubtleShader I absolutely LOVE Pony3 (still one of my favorites out of many hundreds of models tested), so a similar full or hybrid Illustrious version would be something amazing imo.
Seems everybody is moving to LCM/DMD2 these days and the image quality and realism is outstanding, so I completely understand going in that direction.
@AFD_0 Maybe I'll just release a photorealistic version with a bit of a Illustrious touch.
Uploading like a clockwork
I got lucky that I did not need to do any merging this time. Otherwise would have been delayed by a few days.
sharp pussy:1.5
LOllerr
SubtleShader
tell me please, how better use this checkpoints in workflow... photo3 mean that it include all of previous versions with this title? does this include insta1 too? or better use it separate?
Just use the ComfyUI workflow that is linked in the description. Photo3 offers all features of the previous Photo & XL versions. Insta1 was trained on different images, so does some other stuff. Pony is different too. The XL versions have a different style and less concepts.
@SubtleShader thanks!
Hey Shader! I purchased the model back when it first started being hosted on TA. I'm not able to download the Photo3 model with my purchase history. Just trying determine if there's a charge for the new model or if it hasn't been made available yet. Thanks as usual for the great work. Also, any new concepts in this one or was this aimed at improving the existing ones? Thanks!
Yes, there is a charge for the new model. It is located here. New concepts are only fashion photo, detailed eyes and teeth. Some old concepts were renamed to avoid side effects when prompting, e.g. ball sucking/licking to testicle sucking/licking or bubble butt to round ass. The main purpose of Photo3 was to make the concepts work better by using a new strategy that trains them better and avoids merging. It worked.
@SubtleShader Thanks for the clarification. I'll pick it up tomorrow and take it for a spin!
@SubtleShader detailed eyes alone worth it, if its working with full body shot.
Any chance of asp 2.5 seeing any big love?
The bigASP 2.5 weights are not compatible with SDXL. So you cannot merge it with any SDXL checkpoint in a way that makes sense. You can only train it on its own once its creator supplies training software for it. IMO it is a dinosaur that is likely to get extinct.
Prompt adherence must be good but quality not that good due to oily and rubbery plastic skin, can be easily detect as Ai image in 1 sec.
Sounds like you used the wrong settings or a really bad prompt. Big Love is popular for its skin texture. If you get plastic skin, you are clearly doing something wrong.
@SubtleShader all the images in the Galley don't lie
@haidensd58757 Easier to look at a checkpoint for fault than your own skills. You can wrangle out additional quality if you know how to prompt it well.
@SubtleShader The images do look synthetic
@2P2 Do you know any AI model that can do real life looking photos? I don't know one. SDXL is the most photorealistic one available.
@SubtleShader Other new models get always some smartphone(older) lora, which looks very casual and lifelike. If you have casual phone photos, you can add to dataset.
@haidensd58757 Anyway this is not Flux-style plastic skin. And oily, if only you want. Nah, base Flux is, what unusable without loras.
@javenwinson355 Big Love can already do smartphone selfies. There is also a real life concept. You can do amazing stuff if you invest a bit of time in prompting.
@SubtleShader I know it can, but some reinforcement doesnt hurt.
@javenwinson355 Amateur style is not actually more realistic, it's literally just less detail.
I wouldn't say rubbery. It's not flux skin. But the dataset likely contains a mixture of amateur shots and studio lighting, which might bias it towards shiny skin.
@lauraknopek8329 Can't say that generally. Certainly true for certain prompts, but not for others. Real amateur photos are often softer and less crisp. But you can also prompt for amateur and get more average faces with good details. But I don't expect too critical people to have taken the time to explore all nuance of Big Love.
@lauraknopek8329 Shiny skin is rather the result of bad settings and prompts.
@SubtleShader I was speaking generally about amateur photography sources. They have less detail on things like skin than professional photography. Which is why it's often used as a realism hack. Less detail = easier for AI to do.
@lauraknopek8329 OK. But when a checkpoint is trained, it does not simply learn to replicate the images, but rather learns general concepts. So with good prompting you can reproduce an amateur look while generating good details. You can seperate different aspect and only reproduce the good ones.
@SubtleShader My comment was directed to the person who asked for amateur style as a form of greater realism. It was not a critique of your model, nor a comment on training processes.
Do you have a pose wildcard? My prompt is long and many details on the girl. Where to put the sex action?
My prompt: blabla, detailed descripton of the girl, have sex with man?, sex pose?, blabla
I would put the sex stuff first if it is about that. I posted some wildcard stuff here but löst deep in the comments. Will repost later here.
Pose wildcard:
legs spread
backside
lying down bend over ass up
bent over
look over shoulder
showing ass
all-fours
squatting
leaning forward
on the floor
sexy pose
seductive pose
stripper pose
lying on side
sitting
prone position
knee-chest position
kneeling
laying
crossed legs
on back
on side
on stomach
sitting
crossed legs
straddling
standing
legs apart
between legs
hands on ground
ass up
from behind
top-down bottom-up
leaning into viewer
ass grab
breast grab
cupping chest, hands on own chest
dynamic pose, motion, candid
kneeling
legs parted, hands on knees
Big Love sex poses:
1girl, hetero, 1boy, oral, fellatio, penis
1girl, 1boy sucks nipple, breastfeeding
1girl, 1boy, handjob, holding penis
1girl, anilingus, tongue in anus
2girls, 1boy, threesome, sex
1girl, 1boy, on the side, spooning, sex
1girl, 1boy, sex, ass, pov
1girl, 1boy, from behind, sex, doggystyle, pov
1girl, 1boy, view from behind, anus
1girl, 1boy, sex, doggystyle, side view
1girl on her fours, side view, doggy style sex with a man, sex from behind
1girl, 1boy, sex, missionary, pov
1girl, 1boy, sex, reverse cowgirl
1girl, 1boy, sex, lying, ass, 1girl on top
1girl, 1boy, sex, laying on side, leg up
1girl, lying on side, one leg up, 1boy, sex from behind
1girl, 1boy, sex, spooning, anal
1girl, 1boy grabbing breasts from behind
1girl, 1boy, standing split sex
1girl, 1boy, deep penetration, lying on side, dynamic view
@SubtleShader Wow, how can I access to full wildcards, that this model works? Sorry if the question is stupid, I am kinda new to SD at all
I always look forward to your models! I was excited to see this one. Thank you for all your hard work and contributions. Now I am going to go generate images.........should be fun as always.
Thanks for your kind words.Would be nice to see some of your images.
Future Big Love Versions
Lust1: A finetune of Lustify 7 with the look, style & concepts of Photo3. Will likely be released next. Looks promising.
Illu1: Finally making some progress. Already gave up. As it contains Illustrious, it will be less photorealistic but still interesting.
Art1: Trained on artistic images and photos. Will do photo art as well as semi-real. Training set evolving nicely.
Photo4: Will offer new concepts. Still working on the sets.
Ultra1: Similar to the Photo versions, but trained on a higher 1536 pixel resolution. Will do 1280x1920 by default in txt2img. Maybe more.
These projects would not be possible without the people supporting my Early Access releases on Civitai and by activating Big Love on Tensor Art. So a big thanks to you guys!
This is amazing! But have you abandoned Pony/Ponyv4? So far Pony3 gives me the best results by far but it lacks in terms of concepts compared to Photo2.
@EZSpectre Yes, but Pony is less easy to prompt, harder to train and less photorealistic. As Pony3 was only half as popular as XL4, I don't plan a Pony4 version at the moment. Sorry.
Ultra1 definitely has my attention, and should have the attention of everyone that values the speed and efficiency of SDXL over the small style/composition improvements that FLUX offers when generating adult content. FLUX is amazing for corporate style stock art, but there are several SDXL models that mop the floor with it for adult content already, and being able to generate at those resolutions without the body stretching would make that model the go-to for tons of people.
@jdood Thanks. Actually I decided to release a Ultra version of every new Big Love version. So far it is still experimental, but results are already amazing. More photorealistic and detailed. A special quality that cannot be achieved by just upscaling. Image sizes of 1280x1872 and 1360x1984 work best. Can be easily upscaled to 6 megapixel.
However, it needs more training and also takes 2.25x longer to train. I need to expand my high-res training set, which will take time as it is more work. Until then the Ultra versions will require more attempts to produce usable images, more prompt tweaking and seed hunting than the normal version.
Would be good an alt version without the yellow monster.
I love this version. Is there a tutorial for training a lora for this model? I've done a few loras but never tried using this model as base. Any tips or links?
Get OneTrainer, click the SDXL lora preset, select Big Love as the base model, add your images as a concept, then click "Start Training". It is the same for all SDXL models.
@SubtleShader wow, I didn't know that. I have a 12gb RTX and I did some loras but I didn't know OneTrainer. Thank you
Hey there, Subtle! I just bumped in to say thank you, 'cause ur models are amazing. I love the way that thing work, actually I started my way in SD & AI at all with your models (Photo1, Photo2) recently.
One of the things that I like, that actually you provide a info how to work with your models, the trained concepts, prompt guides. And the language, how you describe all this is completely user-friendly.
As for me, I tested couple of models, actually I got some kind of hyper-fix on things when I just start up something.
As for me, the best of Photo models is the prompting. You said that it is kinda of experiment, but based on guide (not yours, but one you send links to), I 8-9 times out 10 got what I wanted.
So thank you again!
P.S
One more funny thing, I got on custom LoRa (Eldritch Comix), and your model Photo2 was the only one that provided good results, even hyped CyberRealistic couldn't work good with it.
Thanks. Happy to hear. Will try to find some time to do a more detailed Big Love prompting guide.
Is there any POV nsfw in the new datasets? Seems maybe weaker on that than the original merges. Like seems to have a bit of a voyeur perspective bias (if you say POV, maybe half or less will be that)
The Photo versions are more creative with perspective as there are various concepts with unusual perspectives. I only trained female pov and follow me pov, no other pov concepts yet. Likely not enough to generalise to other pov prompts. Will try to train more pov. Thanks for the suggestion.
@SubtleShader That would be excellent :) Your models are absolutely great on realism (possibly the best, in NSFW), and POV is something I like to do a lot. There's a lot of photoshoot promo stuff from VR that's very useful for this, such as on vipergirls, if that's helpful.
follows prompts very poorly
What type of prompts? Compared to what checkpoint? Compared to how you would like it to work? It follows my own prompts very nicely. But I invested a bit of time to find out how to prompt it.
According to your pics, yes, its not illustrious level sex adherence. Plus you are using an anime model, which is even more easy to prompt. You need to reset your prompt, if you want to use realistic xl models.
If you wants Illustrious-style sex images, you should use Illustrious. Not Big Love. Otherwise learn to prompt SDXL properly and adjust your expectations. I'm not interested in unrealistic anime sex images regardless of prompt adherence.
Hey @SubtleShader, I'm one of the customers of your models. I've using them for months and I noticed XL4 to produce better quality images than Photo and Insta. The settings and prompts are the same during the tests. The tests are bare-eye tests. The settings are
CFG 1, LCM + Exponential, Steps 5-7, 1200x1200, 1200x800, etc.I'm using at least 8 steps and 1024x1496. With 5-7 steps and lower resolution the Photo versions are definitelly doing worse than they can do.
Anyway, tastes are different. I got people telling me that Pony or XL2 produce better images. Others tell me Photo2, Photo3 or Insta2 create better images. Sure, some prompts work better with certain versions than others and it always depends what you want to achieve, what loras you use and various other things.
I did at least 5k images of each Big Love version with 2k+ prompts. I don't think anyone else has a better overview. If someone is doing just a few dozen images or a dozen prompts, it is easy to come to different conclusions.
@SubtleShader Thanks for your answer. I will keep exploring.
@H4rryM3ss The XL versions definitelly have a more artificial and less refined look than the Photo versions. But some people prefer artificial and cute, some people prefer the Pony look and so on. I always strived to push SDXL into the photographic direction as much as possible. And I saw quite some progress with that during the latest versions.
does Photo3 have watersports/pissing?
It has the squirting concept trained. Pissing works too.
@SubtleShader does that include male pissing?
@qustionauthrity838 Nope. Maybe already works. Did you try?
Big Love Ultra
I decided to release a Ultra version of every new Big Love release. So far it is still experimental, but results are already amazing. More photorealistic and detailed. A special quality that cannot be achieved by just upscaling. Image sizes of 1280x1872 and 1360x1984 work best. Can be easily upscaled to 6 megapixel unlike the normal low-res version.
However, it needs more training and also takes 2.25x longer to train. I need to expand my high-res training set, which will take time as it is more work. Until then the Ultra versions will require more attempts to produce usable images, more prompt tweaking and seed hunting than the normal version. But definitelly worth it.
Its amazing how much you still can upgrade this models.
Good seeds are urban legend.
@zurigarv307 Very practical reality. Urban legend for people who never try different seeds 🤣. Thanks for the laugh!
@SubtleShader What?:) I use wildcard and 100 pics batches, than switch to different seeds. What the heck are you talking about?
@zurigarv307 No idea what you talk about...
@SubtleShader Are you retard? I said, i switched constantly seeds. I refine my prompts, instead of waiting for a good seed to help me.
@zurigarv307 No need to get insulting. Good seeds are very real and no urban legend. Only a fool would prioritize seeds over prompt. So sorry, that your initial comment makes no sense to me.
@SubtleShader "Good seeds are very real and no urban legend. Only a fool would prioritize seeds over prompt"
Ok, im the retard, because, thats oximoron to me.
"An Ultra version for every new Big Love release." Is Lust1 the Ultra Version, or are you saying that Lust1 will come in two available versions to download? Base and Ultra?
@Novellus No, I will release Ultra1first. Based on Photo3. Insta1 & Lust1 are less popular than the Photo versions, so not sure if there will be follow-up releases of them.
Ultra is different from the normal lowres versions. Still need to expand & improve the training set. Will take some time. I would need to collect only hires images to do both lowres and highres versions. Impractical & too much work. So Photo & Ultra will be slightly different for now.
I'm a newcomer; which version is more stable in terms of sex action? Thanks a lot
Photo3 concepts work the best including the sex concepts.
is I need dl lust1 or keep on photo3?
@yazi6393wy136 Lust1 has a slightly different style and other faces. Same concepts as Photo3 plus concepts of Lustify 7. Photo3 does more creative posing. Lust1 has more stable anatomy because it does more standard posing.
this model better work then the insta1 at my pc. and it started do better feet!!! thank you! idk why but close-up generations become over detaliseted and riuned pics
I guess you mean Photo3. Reduce DMD2 strength to 0.85 to 0.95 to reduce details and add more softness.
If I understand correctly, photo 3 will be already released in ultra version?
I have to see. Maybe I will do Ultra1, Ultra2 etc versions after all. Still have to figure out how to train them best.
Great model! Though I have a question, how to get rid of tanlines as negative prompt doesnt work?
This extension lets you use negatives in the positive prompt: https://github.com/hako-mikan/sd-webui-negpip
Other than that you can try "no tan lines", but I just noticed that it may actually produce tan lines. Will need to rephrase it to "even skin color" or something like that before training again.
Tan lines usually occur in certain context like beach, summer, outdoor bathing. You can avoid that context.