A model I originally finetuned for making my cartoon/anime loras - but I accidently ended up just making a model and kept iterating on it. Be careful -- the danbooru images I used tends to move it into NSFW territory. Use danbooru tags. All images straight from the model -- no lora, or inpainting. Use Art by __________ as first tag. Can do SFW or NSFW. List of Artist Styles for Dynamic Prompt can be found at <a target="_blank" rel="ugc" href="https://files.catbox.moe/w413ru.txt">https://files.catbox.moe/w413ru.txt</a> Comparisons can be found at <a target="_blank" rel="ugc" href="https://mega.nz/folder/gf1xlKBI#FNRxuVUAU-fjx_khegWYhA">https://mega.nz/folder/gf1xlKBI#FNRxuVUAU-fjx_khegWYhA</a>Blah blah blah buy me a kofi <a target="_blank" rel="ugc" href="https://ko-fi.com/digimdkofi">https://ko-fi.com/digimdkofi</a>

AnimeConfettiTuneXL

animeconfettitunexl_depConfetti4you.yaml

animeconfettitunexl_depConfetti4you.safetensors

DEP.confetti4you

ConfettiSep2024

DEPMoreConfettiAlpha0.3

DEP. MoreConfettiAlpha0.2

DEP.MoreConfettiAlphaTest

Con5tiXL

DEP.Anim3Conf3tti

DEP.LifeIs2ufferingFP16

Dep.LifeIsSufferingFP16

Dep.LifeisSuffering

Depreciated v. 1.0

animeconfettitunexl_con5tixl.yaml

animeconfettitunexl_con5tixl.safetensors

Trying out a few different options for the training since it stalled a bit. I'm still running tests on this one,

animeconfettitunexl_dep.yaml

animeconfettitunexl_dep.safetensors

THE NEWEST MODEL IS WIP, STILL NOT FULLY TRAINED THIS MODEL IS CREATED WITH KAIREN's PERMISSIONGoal : Remix everyone's favorite 4.0 Homosimile with new twist, hopefully a betterment. And maybe after more training we can have something unique as well.Refined HomoSimile XL [Pony, Illustrious, NoobAI] with bunch of images.Original -&gt; <a target="_blank" rel="ugc" href="https://civarchive.com/models/964011?modelVersionId=1837143">https://civarchive.com/models/964011?modelVersionId=1837143</a> Created by GAIJourney <a target="_blank" rel="ugc" href="https://discord.gg/A3RTYYkCHY">https://discord.gg/A3RTYYkCHY</a> (join the gay AI artist community)Visit <a target="_blank" rel="ugc" href="http://MaleAI.com">MaleAI.com</a> for prompts helpSome example for comparison<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/f2f07898-26ee-49a9-b1a8-e81153e2b9b6/original=true/f2f07898-26ee-49a9-b1a8-e81153e2b9b6.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ca97f4f7-f521-4048-a451-86db1e3df91b/original=true/ca97f4f7-f521-4048-a451-86db1e3df91b.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ac4864ac-80f0-4407-9d6a-b51ed243aea5/original=true/ac4864ac-80f0-4407-9d6a-b51ed243aea5.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3265171e-a21d-4d20-a376-89fd5aa83b72/original=true/3265171e-a21d-4d20-a376-89fd5aa83b72.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/b9197e5f-f06c-4126-ba08-9572ec5ea652/original=true/b9197e5f-f06c-4126-ba08-9572ec5ea652.jpeg" />

MaleAI [Pony, Illustrious, NoobAI] Gay Homo Man Men Male homoerotic

maleaiPonyIllustriousNoobai_v12.yaml

maleaiPonyIllustriousNoobai_v12.safetensors

v1.2

v1.1

v1.0

maleaiPonyIllustriousNoobai_v10.safetensors

maleaiPonyIllustriousNoobai_v11.yaml

maleaiPonyIllustriousNoobai_v11.safetensors

maleaiPonyIllustriousNoobai_v10.yaml

A finetune of animagine XL 3.1 with Ishikei art style, trigger word is optional. Base model: <a target="_blank" rel="ugc" href="https://civarchive.com/models/260267/animagine-xl-v31">https://civarchive.com/models/260267/animagine-xl-v31</a>

Ishikei Style - Animagine XL 3.1

ishikeiStyleAnimagine_v10.yaml

ishikeiStyleAnimagine_v10.safetensors

<h1 id="dandd-battlemaps-af2wa21j1">D&amp;D battlemaps</h1>The model is trained on fantasy battlemaps, so it works the best for medieval fantasy setting but not only limited to this.To install just put both checkpoint and config files to your model folder and keep same names for them.<h2 id="resolution-26g4ngorr">Resolution</h2>You need to use width and height not less than resolution 1024 but you can make it larger and that works perfectly just producing bigger battlemap.<h2 id="dimensions-9qh5wh4tx">Dimensions</h2>You can assume battlemaps dimensions as approximately 24x24 squares (120x120 feet) for normal dimensions of specific model, for example:<ul><li>1024x1024 generation is 24x24 battlemap</li><li>1536x1024 generation is 36x24 battlemap</li><li>2048x1024 generation is 48x24 battlemap</li></ul>And so on. But it can be depending on concept.Grid can be produced unintentionally but it very unlikely and also depends on concept.<h2 id="prompting-o8vcvos1l">Prompting</h2>This model has no trigger words but you can refer to the graph below. X axis is tag words and Y axis is how often it was used in dataset. It is not complete tag list but these should work more or less reliable. <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/bb14e5b2-a7bb-46da-b743-41443c5e13d9/width=525/bb14e5b2-a7bb-46da-b743-41443c5e13d9.jpeg" />Captioning on dataset was made not with natural language but with tags, for example "Forest, river, bridge, road". However I did not found significant difference between these prompting types on tests. Feel free to try both and share what you prefer.<h2 id="settings-iwoj23bri">Settings</h2>Steps: 30Sampler: DPM++ 2M SDESchedule type: KarrasCFG scale: 2.5Size: 1024x1024Sampler - I did not tried, so you can experiment and share your favorite.CFG - you have to use pretty low values between 2 and 3. On 7 it feels really overtrained and burnt but hopefully later i will fix it. It is especially bad with high contrast concepts, like "Lava" or "Winter" and in these cases go CFG 2. In others I prefer 2.5 or 3.<h2 id="tips-and-tricks-wvsq56o8w">Tips and Tricks</h2><ul><li>Try <a target="_blank" rel="ugc" href="https://github.com/hako-mikan/sd-webui-regional-prompter">regional prompter</a>. You can produce something like this in one generation:</li><li><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/f09ca6b8-5f33-4d5a-8af4-9e824fe00178/width=525/f09ca6b8-5f33-4d5a-8af4-9e824fe00178.jpeg" />Try draw a simple scheme of map and img2img it with denoise about 0.75</li></ul><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/4f295f28-6b9c-49e3-8078-39dda4f0c6a4/width=525/4f295f28-6b9c-49e3-8078-39dda4f0c6a4.jpeg" />-&gt;<ul><li><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/550f9abf-72bd-453e-b647-9d9187741b1d/width=525/550f9abf-72bd-453e-b647-9d9187741b1d.jpeg" />Try make scale "Smaller" with same composition. Resize generated image (for example x2) with denoise 0.5.</li></ul>This one looks like 24x24<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/faeb442d-12c0-4576-94df-eb0906ff5c15/width=525/faeb442d-12c0-4576-94df-eb0906ff5c15.jpeg" />And this one is around 48x48 -&gt;<h2 id="p.s.-nb6feqdae"><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/42c1d10a-cda8-4f6d-86f8-27d761080001/width=525/42c1d10a-cda8-4f6d-86f8-27d761080001.jpeg" />P.S.</h2>If you want to support new models release, you can share battlemaps you have. That would be perfect if they will be same style, good quality and no grid. Also I really want to try something not medieval fantasy, for example cyberpunk or postapocalypse like fallout.

D&D Battlemaps SDXL 1.0

dDBattlemapsSDXL10_v10.yaml

dDBattlemapsSDXL10_v10.safetensors

Upscale v1.0

Provides more defined characters and backgrounds and can improve character/style LoRA accuracy compared to the base Pony V6 model.<a target="_blank" rel="ugc" href="https://files.catbox.moe/ptls1c.txt">Characters included in the base model</a> have their own style which you can override with artist prompts or style loras.<h3 id="recommended-positive-prompt:-score_9-score_8_up-score_7_up-source_anime-aj9egojdb">Recommended positive prompt: <code>score_9, score_8_up, score_7_up, source_anime</code></h3>For western style replace <code>source_anime</code> with <code>source_cartoon</code>If using a character or style LoRA and its style is not preserved remove <code>source_anime</code>. Can also remove <code>score_8_up, score_7_up</code> if the LoRA style is still too weak but this usually simplifies the image too much.To use artist tags shown in the examples use <code>art by</code> followed by the artist name.v2 is a 50/50 merge of <a target="_blank" rel="ugc" href="https://civarchive.com/models/184813?modelVersionId=350698">confetti4you</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/models/246299?modelVersionId=313717">Comradeship v5a DPO</a>. v3 is the same but with <a target="_blank" rel="ugc" href="https://civarchive.com/models/184813?modelVersionId=392194">Con5tiXL.</a> Some prefer the 2D style of v2. v3 seems to work better with character LoRA especially with 3D ones.This model is also available as a <a target="_blank" rel="ugc" href="https://civarchive.com/models/496427/anime-confetti-comrade-extract">LoRA extract</a> designed to be used with the base Pony V6 model.All images are generated with Euler A sampling method, 6 CFG Scale using <a target="_blank" rel="ugc" href="https://github.com/lllyasviel/stable-diffusion-webui-forge">WebUI Forge</a>. WebUI Forge is built on top of Automatic1111's backend but has lower VRAM usage and higher performance. Try it out!

Anime Confetti Comrade Mix

Use Confetti4You instead of Anim3Confetti in merge. Changes image composition slightly.

animeConfettiComrade_v2.yaml

animeConfettiComrade_v2.safetensors

animeconfettitunexl_depAnim3conf3tti.yaml

animeconfettitunexl_depAnim3conf3tti.safetensors

animeconfettitunexl_depLifeissuffering.safetensors

animeconfettitunexl_depLifeissuffering.yaml

animeConfettiComrade_v10.safetensors

animeConfettiComrade_v10.yaml

homosimileAgainPony_v10.safetensors

homosimileAgainPony_v10.yaml

Dreambooth Model TestYeah.. its heavyIf you like my model, please consider donating: <a target="_blank" rel="ugc" href="https://ko-fi.com/hikarias">https://ko-fi.com/hikarias</a>I'm open to commissions.

Chloe Bennet Dreambooth

chloeBennet_v10.yaml

chloeBennet_v10.safetensors

Continued training.A model I finetuned for making my cartoon/anime models - Not really designed to be used by itself, but a branch model for making Loras. Be careful -- the danbooru images I used tends to move it into NSFW territory. Use danbooru tags. All images straight from the model -- no lora, or inpainting. Use Art by __________ as first tag. Can do SFW or NSFW. List of Artist Styles for Dynamic Prompt can be found at <a target="_blank" rel="ugc" href="https://1fichier.com/dir/xazkNCbB">https://1fichier.com/dir/xazkNCbB</a> Comparisons can be found at <a target="_blank" rel="ugc" href="https://mega.nz/folder/gf1xlKBI#FNRxuVUAU-fjx_khegWYhA">https://mega.nz/folder/gf1xlKBI#FNRxuVUAU-fjx_khegWYhA</a>.Blah blah blah buy me a kofi <a target="_blank" rel="ugc" href="https://ko-fi.com/digimdkofi">https://ko-fi.com/digimdkofi</a>

!!! IMPORTANT!!!It is not a standalone model, but only for img2img upscaling.!!! IMPORTANT!!!Tired of low res blurry battlemaps? I have solution for you. X2 upscale model released.How to use:<ol><li>Generate base image with original model</li><li>Send it to img2img</li><li>Keep same settings, but set denoise 0.5-0.6 and resize x2 (e.g. 1024-&gt;2048)</li><li>Generate and enjoy</li></ol>High resolution requires more VRAM and if you run locally I recommend you to use Forge UI. This can take a while to generate, but you will get the result if you are patient enough.

dDBattlemapsSDXL10_upscaleV10.safetensors

dDBattlemapsSDXL10_upscaleV10.yaml

Nothing new -- just an FP16 version for those who want it.

Files with SHA256: 7d0032c367d80cb33c4b96a64bfcdc45cc1e46a0996a2da713ceb49a5aed42e3