|
"description": "Im cooking version 1.4SupportYou can check out my Patreon https://www.patreon.com/TianChimp for more results using my models patreon.com/TianChimp https://www.patreon.com/TianChimpReferrals and stuffDiffusionHub: DiffusionHub provides blazing-fast, reliable and private-hosted cloud for Stable Diffusion diffusionhub.io?fpr=tianchimp https://diffusionhub.io?fpr=tianchimpMy modelsHardcore - Hentai v1.3 https://civitai.com/models/136054/hardcore-hentai-13Hardcore - Asian Porn v1.1 https://civitai.com/models/138630/hardcore-asian-pornLore / BackstoryI just wanted a model that could generate high quality art and hentai and that actually followed the prompt. Couldn't find one so I made it myself. Hope you like it and share your generations with everyone!I hope this model doesn't become just another pointless merge that no one will ever use.Using the modelThe best advice I can give you is to experiment for yourself and see what works for you. So you are encouraged to completely ignore this and use the prompts/settings you like and find ways to get the best results out of this and any model.Like Danbooru's Rule of thumb https://danbooru.donmai.us/wiki_pages/howto:tag \"Tag what you see, not what you know\", don't use words that should not be visible in the final image.IE: Don't use words for shoes if you are making a portrait or upper body imagePromptUse danbooru tags or sentence-based prompts.You can use any generic filler prompts like: masterpiece, best quality, high quality, highres, etc..., or none.Extension for tag autocompletion tagcomplete https://github.com/DominikDoom/a1111-sd-webui-tagcompletePrompt Order for good compositionTags at the start have more influence than the ones at the bottom.The 7 blocks template (Work in progress):participants, sex acts, view angle1girl https://danbooru.donmai.us/wiki_pages/1girl, 1boy https://danbooru.donmai.us/wiki_pages/1boy / multiple boys https://danbooru.donmai.us/wiki_pages/multiple_boys,sex acts https://danbooru.donmai.us/wiki_pages/tag_group%3Asex_acts,view angle https://danbooru.donmai.us/wiki_pages/tag_group%3Aimage_composition,posture, positions and secondary actionsposture https://danbooru.donmai.us/wiki_pages/tag_group%3Aposture,sexual positions https://danbooru.donmai.us/wiki_pages/tag_group%3Asexual_positions,secondary actions,head orientation (looking back, looking at viewer, etc...),bodybreasts size https://danbooru.donmai.us/wiki_pages/breasts, stature (petite, tall female, etc...),age (mature woman, old woman, etc...),body fat (skinny, curvy, plump, fat, obese, narrow waist, etc...),hairhair color https://danbooru.donmai.us/wiki_pages/tag_group%3Ahair_color, hair style https://danbooru.donmai.us/wiki_pages/tag_group%3Ahair_styles,clothing or lack of clothesclothing https://danbooru.donmai.us/wiki_pages/tag_group%3Aattire,face expressions, cum location and eye colorface expressions https://danbooru.donmai.us/wiki_pages/tag_group%3Aface_tags,eyes https://danbooru.donmai.us/wiki_pages/tag_group%3Aeyes_tags,cum location https://danbooru.donmai.us/wiki_pages/cum,scenery and otherslocation https://danbooru.donmai.us/wiki_pages/tag_group%3Alocations,furniture and objects that should be visible,stylescharacter (probably only if it was released / popular before early 2023)(hatsune miku, ganyu \\(genshin impact\\), etc...)You don't need to fill in every category, it's just for reference.Negative promptYou can just use EasyNegative or some of the generic prompts:worst quality, low quality, bad quality, normal quality, bad anatomy, monochrome,And whatever you don\u2019t want to be on the imageSome people use the standard (worst quality, low quality: 1.4) + negative embeddings with good results too.If you use too much emphasis, like (worst quality:2.0) you'll start getting burned images.SamplersYou can use any sampler. Some samplers converge at a defined image, others keep changing with each step. You can find better explanations here https://www.youtube.com/watch?v=JAMkYVV-n18 and here https://stable-diffusion-art.com/samplers/.I'd say the top choices are:DPM++ SDE Karras (slow)DPM++ 2M Karras (fast)Euler a (fast)DPM adaptive (slow)DPM++ 2S a Karras (slow)DDIM (fast)Steps25 - 50CFG7: standard3\u201315: working rangeLower cfgs don\u2019t follow the prompt as much. Higher cfgs will make \u201cburned\u201d imagesThe extension sd-dynamic-thresholding https://github.com/mcmonkeyprojects/sd-dynamic-thresholdingcan play around with different CFGs at different stepsSizes1:1\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 [512, 512], [768, 768]2:3\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 [512, 768]3:2\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 [768, 512]You can use Hires fix to get a bigger picture with more detailsUpscalingI'm getting good results with Hires fix enabled.Upscaler: Latent nearest-exactHires steps: 20 - 50Denoising Strength: 0.5 - 0.55Upscale by: 1.5 - 1.875Denoising at 0.5 seems the most stable for preventing duplicate body parts and body horrorsLatent upscalers tend to create more detail while upscaling, the rest of the upscalers don't add too much to the base image with the same settings.VAEThere are many VAEs out there. These are the 3 most popular.kl-f8-anime2 https://huggingface.co./hakurei/waifu-diffusion-v1-4/blob/92e0470e5a9601cdd85a3db349a591df9ed7e2ad/vae/kl-f8-anime2.safetensors for vibrant colors and anime face/eyesorangemix.vae https://huggingface.co./WarriorMama777/OrangeMixs/blob/main/VAEs/orangemix.vae.pt for muted colors and anime face/eyesvae-ft-mse-840000-ema-pruned https://huggingface.co./stabilityai/sd-vae-ft-mse-original/blob/main/vae-ft-mse-840000-ema-pruned.safetensors for vibrant colors and real face/eyesBaked VAE for each version.v1.0 has vae-ft-mse-840000-ema-pruned.VAE baked in.v1.1 has vae-ft-mse-840000-ema-pruned.VAE baked in.v1.2 has vae-ft-mse-840000-ema-pruned.VAE baked in.v1.3 has kl-f8-anime2 VAE baked in.The [no VAE] variants don't have any VAE baked in.PermissionsJust use the model and share your generations here or wherever you wantI\u2019d appreciate if you link to this model page when sharing your generations \ud83d\ude0aI made a patreon if you want to support me https://www.patreon.com/TianChimp https://www.patreon.com/TianChimpPlease share your generations!Tag considerationsI've noticed some tags having too much influence over the entire image resulting in a loss of style and quality, but sometimes they are necessary for your target composition. This is probably only noticeable on <75 token prompts.You can try setting lower influence with parentheses IE 0.5 - 0.9 Needs more testing but I'll keep a list of potential suspects.fellatio (tends to put hand around the penis)cum (variations)multiple boysFAQ - Frequently asked questionsMy images look desaturated, with dim colorsYour software is probably missing/not using a VAE. The main model v1.1 doesn't include one, so you can use any VAE you want. The model v1.1 [VAE] comes with the standard VAE https://huggingface.co./stabilityai/sd-vae-ft-mse-original/blob/main/vae-ft-mse-840000-ema-pruned.safetensors baked in, so it uses that VAE and ignores the selected one.Different interfaces have different ways of selecting the VAE. In Automatic1111 you can set a VAE selector next to the model selector by going to Settings > User Interface > Quicksettings list, and adding \"sd_vae\".(Apply Settings and Restart UI)That'll result in your interface looking like this:Your vae selector will look for files located in your VAE folder, like \"SD-1.6\\models\\VAE\", so you have to download the VAE files you want and place them there.", |
