Big Love Klein3 is also offered for $10 on Tensor Art. You can 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! A subscription includes the latest release and new ones within 30 days. Any problem? Contact me via chat.
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 Klein is a fine-tune of Flux 2 klein. It can do txt2img and also edit images with prompts. It only needs 4 steps, so is quite fast. Check the "About this version" box on the right for info on the individual variants. Some are up to 3x faster.
It is recommended to use it with ComfyUI. 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.
Settings are 4 steps (2 steps for upscaling), cfg1, Euler sampler, Beta scheduler, 832x1216, 1024x1536, 1280x1920 or 1536x2240 pixels
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. Check the "About this version" box on the right for info on the individual variants.
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 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, 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, Qwen, 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
Photo2 is more photorealistic, more creative with perspectives, avoids oversharpening and oversaturation (less processed than Photo1/XL4). It was trained on 2250 images and 40 new concepts: 3d selfie, 69, 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.
FAQ
Comments (67)
any recommendations how to get prompts like "playful wink with kissy lips" going to work?
I don't want to oversell Photo2, but it has changed my life forever. Best money ever spent.
agreed, one of the few creators I'm happy to drop 10k buzz on
I buy in seeart...but can't find Photo2 to download
Photo2 is not on Seaart.
A no-brainer to get this during early access, worked with the same setup as photo1. But a question I've had since using photo1, I see a lot of green, be it green walls, clothes, etc. Is this a model issue or can I tone it down with negative prompts? I'm currently using the dmd2 lora with NAG ksampler, lcm, ddim_uniform, 6 steps, 1 cfg. I can use the same setup on another model and I don't get random green things. Other than that, the model follows promos exceptionally well, except for multiple people but I think that's my latent size. Very good, 7$ well spent. No regrets.
Sorry to hear. I don't get too much green. I don't use ddim_uniform and NAG, so that might be the problem. 6 steps is a bit low. I never needed to use a negative, can be fixed in the positive prompt too.
@SubtleShader I figured it was my own setup, so thank you for confirming my suspicion. I'll try to follow your instructions and look for improvements on my part.
Photo2? Bro moving like Apple these days XD ... okay I'll get it.
Photo 3 concepts: sexy perfect eyes out of box(no adetailer, hires, upscale), clothes and materials, lowleg leggings doesnt mean, its on her ankle, no overfucked pussy with overfucked labia(its not even realistic).
Thanks for the suggestions! You can always get better details by upscaling/detailing, because there are more pixels. Why eyes look better in txt2ing with portrait as eyes occupy more pixels. But sure I can train eyes.
What is a overfucked pussy/labia? 😆
@SubtleShader :) You know, after all the base was trained on mostly pornstars, amateur porngirls:)
@rishikbreton421 So you want younger pussies? 😊 Sure, will try to collect some more diverse pussy images. Thanks for your suggestions! Eyes and pussies. Ay ay, sir!
@SubtleShader Thanx man.
you can't train things that are bounded by the model resolution, do a two pass upscale workflow
Thanks for this release. I will buy again, definitely. I still push for throat or vore uvula and just uvula concepts.
BigLove is the only thing that makes me believe A.I has a future...
I'm not sure about V2 because I haven't tried it yet, but for future training it would be good to have a solid understanding of "pants down" (to knees/ankles etc), and "hand down/in pants/panties". These things are hit and miss with V1, they can work, but not consistently. Great model btw, a step up from everything else! V1 reminds me a bit of the first release of BigASP, could be a great base for other future models.
Thanks. I added "pants down" and "hand in pants" to my list of concepts.
Impressive, the speed with dmd2 fp16 and fp32 is great. Quality is good too. Thank you for this model.
This Photo1 is IMO by far the best checkpoint to train a LoRa for likeness on! It's amazing how well anatomy and facial likeness are captures. I've tried a lot of different trained models but I always fall back to the vanilla SDXL checkpoint. But this model truly is better (as long as you go for photorealism). I can't wait to train Photo2.
The LoRas work flawlessly with other checkpoints. Funny enough I find the LoRas work even better with other checkpoints than it's parent one.
Small tip for OneTrainer users: turn on "Generalized offset noise with a value of around 0.12. This should counter the loss of contrast when training on this model.
Thanks for the tip and praise! I noticed myself that loras trained on Big Love produce better quality with other checkpoints too.
@SubtleShader It really takes the "copy" two steps further. And the results are really natural. There is some magic going on. :)
@Sanchez3 The magic is training with good images on top of an already good checkpoint. Makes Big Love more and more photorealistic with each new version.
Does anyone know if the Candidness Loras work correctly in XL4 and Photo1? I know they were made to work with XL2 originally
There is no correct. Might just be that the effect is weaker. But Photo1 was trained on 50% of the Candidness training images. Just add amateur photo to your prompt.
Hey everyone! Do you have a method or workflow to achieve perfect face consistency? I’ve been struggling to keep it consistent when using ControlNet/IPAdapter, and even with a LoRA it’s hard to maintain the same face across different angles, distances, etc. Any tips or workflows you could share would be super helpful!
You are asking for the holy grail. You can only try to make a lora as good as possible, use consistent prompting and maybe a bit of controlnet. In the end you need to generate a lot of images and pick the most similar ones.
Yes I know haha ^^ I’m just looking for advice on the best settings and methods to train a LoRA, and techniques that give the best results when using it. For example, first base generation then face-only inpainting or any other useful tricks people want to share :)
Your models are just so amazing! I’m really trying to get the best out of them, but I’m struggling with face consistency when I use ControlNet, IP-Adapter, and DMD2. I’m having a hard time finding the best settings (steps, CFG,....) and the weights for the IP-Adapter and ControlNet.
@influaipro749 Character consistency is the toughest shit. I don't envy you. Use the recommended Big Love settings.
I stumbled across a comfyui workflow yesterday on seaart that finally gave me the face I wanted without having to worry about training a LoRA. It's called "reactor face swap sdxl" I just uploaded the image of the face I wanted. Then selected big love model added a Lora into the workflow for the DMD2 and then changed the settings to the way I normally run big love and the face transferred perfectly. However, I did notice that it really needs to be a high res quality image of the face or you will have blurring and a lower quality face with much higher quality on everything else
@MyaSturbate Thanks for the tip! I’ve already tried that method, but my results aren’t that great when I change the angle / pose or on long-distance (full-body) shots. How does it work for you in those situations ?
Way better than Photo1 and pretty good in most cases. Unlike the older versions I found Photo1 was unusable at 8 steps (comfy) and would probably stick with 6 for Photo2 as well.
Thanks. 8 steps are fine in Forge.
I wish others would also bid on this for the auction. These models are by far the best that I've seen. I don't understand how there aren't more who appreciate it properly.
The Civitai generator is low quality when it comes to photorealism. Pony might work. Why I recommend Tensor Art, which produces almost as good good quality as generating local. The other problem is that now only 100 checkpoints are allowed on the generator, which makes bid price too high. Not worth it. I would lose buzz.
@SubtleShader makes sense, thanks. Sounds like I need to check out Tensor Art. Thanks!
If you're planning on doing another checkpoint, can you please include rimming and anilingus?
Yes, I already have training images for that.Will be trainec with Photo3. It is already possible as you can see from some of my images, but additional training will improve it.
@SubtleShader I didn’t know it was already possible: how do I trigger it?
@qustionauthrity838 annilingus works. Rimming might work, but did not try. Ass licking works.
@SubtleShader Please train female-to-male rimming
@qustionauthrity838 I think I covered all variants
add "anal prolapse" and "prolapse fucking"
Big Love Insta1
I'm working on a new version of Big Love focused on a Instagram-like SFW look. After Photo3 I plan to do Big Love Art1 for generating artistic images with a photorealistic look. If you have suggestions for other Big Love variants, please let me know.
Sfw BigInsta sounds very good. But biggest flaw of dmd are clothes and materials. Mostly they are just unfinished, a lot times it doesnt care about materials, which is important, if you want sfw model.
@rhetttheo240 Should be enough clothes in the training set.
Maybe a BigLove Pee/Watersports? I know that’s not everyone’s kink, but it is a growing one.
@qustionauthrity838 Peeing works. Photo2 has squirting trained, but it is quite weak.Will retrain with Photo3.
@SubtleShader would especially like male-on-female pissing
Do all these models have a bias towards looking at the camera? When making artistic shots it is often prefered for the model to pretend the camera isn't there, even when he/she is facing it. It would be good to have an easier way to have a more "candid" look to the outputs
@dark_aesop Yes, looking at viewer is pretty standard even if you don't prompt it. You have to prompt looking away or similar things to avoid it. I guess, I should train looking away in Photo3. Thanks for the idea!
Thank you so much for all the work you put in to these.
@SubtleShader Thanks for the reply. IMO that is likely to result in similar photos where the subject is just averting their gaze or looking to the side. The actual difference you want is between a portrait and a candid. Take this for example: https://imgur.com/gallery/example-cpW2ipI The first image is a candid, it's like the photographer and subject exist in separate worlds. The second one, even if the subject is looking away, is actually a portrait. There is intentionality in how the subject is presenting themselves to be photographed. Just something to consider.
@dark_aesop The first image is side view. The second is looking away or looking to the side. Would train the second.
@SubtleShader Basic camera prompts, what xl knows out of box. You dont need to reinvent every basic concept. While adetailer or eye detailer loras are must have to get acceptable eyes with full body shot, you should focus on eyes.
@nolynjhovanny137 I alread have a detailed eyes set. Improving looking direction & head positions should help too. Especially when combined with good facial expression.
@dark_aesop I tend to use "unaware" as a token to help with this, seems to work quite well. Also negs: pose / posed / looking at camera / looking at viewer
Please do a "Cinematic" variant. There has never been a model able to do cinematic shots quite like BigASP2, (especially with that old film look). I don't simply mean dramatic lighting and a "cinematic feel" which plenty of models can do, I mean more that realistic "film still" look. With this model currently being so photography oriented, it's not perfect for those sort of shots.
Anyone else getting too many hands with Photo2? Can't figure out what keeps causing it. Even the ultrares workflow example gives you an extra foot.
Reduce the image size. I use 1024x1496 in txt2img and don't have have problems. SDXL is only trained on 1024 pixel. Even with UltraRes I use 1280x1920, but more anatomy problems.
@SubtleShader thanks, that's got it. I just used the example workflow as-is; might be worthwhile to post an updated example workflow with the txt2img set to 1024x1496 before upscaling.
How do I make a shorter male? All the traditional prompts are making the male taller.
Try a different aspect ratio for the image size
Can this be used for inpainting? If yes how?
As you normally do inpainting.