Version 4 is now live.
*Images are shown without any LORA's or EMBEDDINGS unless stated in their details.
This model is a custom blend of various models, (see below), giving many options for generating a wide variety of images, including NSFW. Based on Stable Diffusion 1.5.
Primarily focused on capturing skin texture and the feel of photography, and Polaroids in general, but experiment with other things. (This model is not perfect).
Though there are is no specific KEYWORD to 'turn it on', if you use words in the prompt such as 'polaroid' , 'analog' , 'film grain', 'perfect eyes' and so forth at the start of the prompt, you should get the look you're after.
The example pictures do not have any face/eye correction or upscaling. 768 x 1024px is quite stable at producing images without 'mutation' if the prompt and neg prompt are good.
The model needs a VAE. (vae-ft-mse-840000-ema-pruned is fine or you can use your own.)
Prompt example:
(selfie)+++, (bokeh)++, RAW photo, (intricate detailed eyes), alone, (shot from the side)+, close up portrait, cheeky smile, (Irish blonde woman), catholic tattoos, thicc, leaning against wall, (wearing undersized vest)++, (looking at the camera), intricate details, skin imperfections, halo of light, midday sunlight streaks spilling over face, face details, unbelievable intricate details, dark shadows, (graffiti covered ruins), real lighting, bloom, volumetric lighting, cinematic lights (ultra skin texture), (symmetrical eyes), light beams streaming through haze
Negative:
Child, Bad eyes, Overexposed, (semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, digital art, anime, painting, manga), (poorly drawn hands, poorly drawn face), (deformed iris), (deformed pupils), grit, man, distorted, male, skin rash, deformed body, mutated hands, poorly drawn eyes, head crop, smooth skin , deformed hands, deformed proportions , long face, long neck, looking away, puffy nipples, watermark, logo, text, multiple people, jewellery, Plastic skin, Overexposed, (semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, digital art, anime, painting, manga), (deformed iris), distorted body, (deformed pupils), grit, man, distorted, (extra arms), long body, male, skin rash, deformed body, mutated hands, poorly drawn eyes, head crop, smooth skin , deformed hands, (deformed proportions) , long face, long neck, looking away, puffy nipples, watermark, logo, text,
A non-exhaustive lost of models merged (because I didn't take notes): deliberate, clarity, dreamlike-photoreal, realistic vision, protogen (+ additional ones in version notes).
Made for fun, not for money or notoriety. Those who train the models from scratch are the ones deserving of applause.
Have fun! Can't wait to see what you come up with...
-
DEPRECIATED INFO:
(Version 3.1 is a hotfix, as the prune for v3 failed and was showing errors on peoples pictures.
(It is very dependant on negative prompts, so use the example images as a base.) The first image uses a light map as img2img so your results may very, but i thought it looked cool so i included it.
The model is better with a VAE. (vae-ft-mse-840000-ema-pruned is fine or you can use your own.)
* For some reason (for V2) the pruned version isn't showing as the first download and the hashes have got screwy. Please use the dropdown menu to choose the smaller version if desired *)
Description
Been a bit of a slog, but here we are... V2 on average gives better eyes than v1, especially for headshots (see examples; no face or eye restore, upscaling etc). I think the skin and lighting are more natural. Defining age is better, but still not perfect (eg: written as 20yo, 60yo or 20 year old). Version 3 will hopefully address this and a few other minor gripes i have with it. Works better with img2img now too. More improvements to come. This time i remembered to include the pruned version.
Thanks for the likes and the kind words (this isnt my full time job, so i cant address everyone's questions i'm afraid, but i'll do what i can)
FAQ
Comments (13)
Thanks for the Simple and Concise description.
test
Did v2 change? There seem to be 2 versions of v2. The version currently posted (hash A4DF55D292) and one with a hash of 71F4DFD701 (see the most recent scottymac Roxie Cipher images).
Hi, i've personally made no changes to the model, so im not sure why the HASH has changed. i uploaded V3 for testing and some bugs were noticed so i removed v3... not sure why that would impact v2 though
@avalon Do you know what the hash was for that version?
@pdavis68373 No, didn't log it I'm afraid.
Oh hi, didn't see y'all chatting about it here. Check out this image: https://civitai.com/images/769990 -- I'm definitely seeing 71F4DFD701 currently and the CivitAI extension is matching it to what I have installed. Weird, right?
@scottymac Yeah, little bit odd. The upload and verification times are still correct, so the model hasnt been replaced. just that odd hash thing. but its very odd. V3 is now ready anyway, (as ready as it ever can be i think) and i'll get it up over the weekend. start again, as it were.
@avalon I don't know how it happened, but there is another version. @scottymac shared his version with me last night and it was immediately obvious that it was different, as instead of being ~4Gb, it was ~6Gb in size. I was able to reproduce that image exactly using his copy of the model. They produced very similar images. Most of the differences were very subtle. The biggest differences were in the background.
@avalon do I somehow have an unpruned V2 while @pdavis68373 has a pruned version?
@scottymac certainly looks that way. its showing me the un-pruned version now when i load the page too.
@avalon Looks like you posted a pruned V3 -- can you also post an unpruned version? I believe a model version can have up to three files so you can have both.
@avalon Also: I'm super pumped for new version!!!
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.




