LoRA trained on 386 Images of Diffuse Texture from <a target="_blank" rel="ugc" href="https://polyhaven.com/faq?q=commercial">polyhaven</a> and manually download and describe <a target="_blank" rel="ugc" href="https://pastebin.com/k5fbiXCM">tags</a> for each one of them... while respect <a target="_blank" rel="ugc" href="https://polyhaven.com/textures">polyhaven tags</a>.I shared my <a target="_blank" rel="ugc" href="https://rentry.org/sddreambooth#dreambooth-config-settings">dreambooth config</a> and the Training Data so that you can reproduce this LoRA, sharing also my process to train my model <a target="_blank" rel="ugc" href="https://civarchive.com/models/3204/berrygold-11">BerryGold</a> on Large amount of anime images.Note<ul><li>SD1.5 can already create texture but <a target="_blank" rel="ugc" href="https://civarchive.com/images/618905?modelVersionId=54923&amp;prioritizedUserIds=42892&amp;period=AllTime&amp;sort=Most%20Reactions&amp;limit=20">not without shadow/reflection</a>.</li></ul>Tips<ul><li>To create AI PBR <a target="_blank" rel="ugc" href="https://github.com/joeyballentine/Material-Map-Generator">use</a> <a rel="ugc" href="https://huggingface.co/spaces/NightRaven109/Diffuse2PBR">2</a> or <a target="_blank" rel="ugc" href="https://github.com/HugoTini/DeepBump">DeepBump</a> or Substance Sampler.</li><li><a target="_blank" rel="ugc" href="https://imgsli.com/MTczODgw/0/2">Upscale comparison</a></li></ul>Related models<ul><li>Checkpoint base on SD2.1<a target="_blank" rel="ugc" href="https://civarchive.com/models/43468/texture-hell"> Texture Hell</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/dream-textures/texture-diffusion">Texture Diffusion. </a>(<a target="_blank" rel="ugc" href="https://withpoly.com/browse/textures">withpoly</a>, <a target="_blank" rel="ugc" href="https://github.com/daveredrum/Text2Tex">Text2Tex</a> <a target="_blank" rel="ugc" href="https://vmod.xyz/">1.</a>), <a target="_blank" rel="ugc" href="https://openmodeldb.info/?t=texture-generation">ESRGAN</a></li></ul>

Diffuse Texture

<a target="_blank" rel="ugc" href="https://pastebin.com/qZXbZEzr">Tags list for v1.0 Experimental_test_2K</a>This checkpoint is meant to generate 2048x2048 images without upscaling! NOT 768x768not a LoRA, but is based on checkpoint 2.1-768, and trained on images with a resolution of 2048x2048.This is a proof of concept for comparing high-quality datasets to 512x512; in the end, 512x512 remains superior.<ul><li>Added 16 textures.</li><li>Added Trigger Words: ", seamless, shadowless" Will be removed in next version.</li><li>Fixed tag list issues by normalizing less common tag variations, along with additional miscellaneous dataset fixes.</li></ul>

DiffuseTexture_11_FULL_sd21-768_2K_16920.yaml

DiffuseTexture_11_FULL_sd21-768_2K_16920.safetensors

v1.0 ExpTest_NO_LORA_2K

v1.1

v1.0

Other download: <a target="_blank" rel="ugc" href="https://drive.google.com/uc?id=1990Jo1FnMuwbBZfWYypBdtecMPFBW0at">https://drive.google.com/uc?id=1990Jo1FnMuwbBZfWYypBdtecMPFBW0at</a> <a target="_blank" rel="ugc" href="https://drive.google.com/uc?id=1zZzJ7jhDQgKGJXnN4BvIzxe7Rtd05TmH">https://drive.google.com/uc?id=1zZzJ7jhDQgKGJXnN4BvIzxe7Rtd05TmH</a>\/ READ THE RECOMMENDED SETTINGS FOR BETTER RESULTS \/Recommended settings:Sampling method: Euler A, (found the best results with Eular A, 2nd best DMP++ SDE Karras)Sampling steps: 24 and higherCFG Scale: 1-3 (go as low as possible)Resolution: if you want to generate girls consistently do portrait 768 which is 624x936 you can mess around with the ratios, landscapes make sure not to go above 1200 res on either height or width and you're all goodTry using portraits for girls and wide for landscapesUsing VAE might make the image quality worseIf the style doesn't show try adding "a painting of..."Try use "text, signature, watermark, username, artist name, trademark," for negative prompts to not get the signature thing.This model was trained on 624x936 936x624 just so you know.This model was original a pretest but ended up pretty good. It has a pretty limited dataset only trained on (Landscape, girl) so if you try generating a man it'll look weird. The final release v2.1 might be out within this month if I gain access to a good GPU to train. The model after that will be v3, it will have easier prompting.This was trained on Niji expressive images I specifically selected then color graded them.(edit the result might not be great if you use these) prompt regularly and you'll get good results, be simple.Here are some prompts you can try:Horizontal:a woman with a sword in her hand and a hairdow in her hair, with a large, feathered headpiece, looks into the distance, NIJIFTBa painting of a rocky path with flowers and rocks on either side of it and a sky background with clouds and sun shining through the trees and flowers, NIJIFTBa painting of a mountain with a lake in front of it and a forest in the background with a few clouds in the sky above it and a few trees, NIJIFTBa painting of a mountain valley with flowers and trees in the foreground and a stream running through the valley below, with a mountain in the background, NIJIFTBa painting of a mountain lake with trees and a house in the foreground and a snow capped mountain in the background with a blue sky and white, NIJIFTBa painting of a man walking through a field with a mountain in the background and red flowers on the ground in the foreground, and a blue sky with clouds, NIJIFTBa painting of a man riding a horse in a mountain valley with a stream running through it and a mountain range in the background with snow capped mountains, NIJIFTBa painting of a landscape with a stream and trees in the background and a house on a hill in the distance with a blue sky and white clouds, NIJIFTBa painting of a house in a field with flowers and a stream running through it, with a sky background and clouds in the sky above it, NIJIFTBa painting of a couple of horses in a field with mountains in the background and a stream running through the grass and flowers in the foreground, NIJIFTBa digital painting of a cat in the snow with snowflakes on it's fur and eyes, with a blurry background of snow, NIJIFTBVertical:a cartoon character with a pink hair and blue eyes wearing a blue dress and pink earrings and a blue dress with pink flowers on it's shoulders, NIJIFTBa cartoon character with pink hair and a cat ears on her head and a black cat outfit on her body and a pink collar and tail on her head, NIJIFTBa doll with red hair and blue eyes wearing a green shirt and pink tie and pink pants and a pink and green jacket with a pink collar, NIJIFTBa woman with blonde hair and blue dress sitting on a floor with her hand on her chin and her hand on her chin, looking to the side, NIJIFTBa woman with blue hair and a blue jacket sitting on a chair with her hands on her face and her hands on her chin, her chin, NIJIFTBa woman with blue hair and a flower shirt on, with her arms crossed and her eyes closed, is smiling at the camera, with a blue sky in the background, NIJIFTBa woman with blue hair and a green shirt is sitting down and looking at the camera with her hand on her chin and her hand on her chin, NIJIFTBa woman with green hair and a green jacket sitting on a stool with her hand on her chin and her hand on her cheek, with her chin resting her chin, NIJIFTBa woman with long white hair and a cat ears hat is sitting on the floor with her hand on her chin and her hand on her chin, NIJIFTB

NijiDiffusion

nijidiffusion_half.safetensors

nijidiffusion_half.yaml

Half

Check out v2 <a target="_blank" rel="ugc" href="https://civarchive.com/models/55495/ahh-v2-nijijourney">https://civarchive.com/models/55495/ahh-v2-nijijourney</a>if you want girl "aptfc"if you want landscape "zgambuf"I found that if you add more to the prompt it ruins the quality.Recommended SettingsResolutions: 912x576 576x912Sampling method: Euler aSampling steps: 72CFG Scale: 1 (try to make it as low as possible)

ahh_v10.safetensors

ahh_v10.yaml

Furrender is a model trained to produce images of male anthro characters that have a 3D rendered appearance. It has strong biases and may not be well-suited as a general-purpose model.Lower CFG values (2-5) work best.Good for inpainting anthro faces, adding fur or scale detail, and altering fursuit images.Merges well with other models.

Furrender

furrender_50.yaml

furrender_50.safetensors

furrender_10.yaml

furrender_10.safetensors

Just in time for Halloween, Monster Diffusion is back and is an enhanced version of the original Monster Diffusion model, now leveraging the power of Stable Diffusion SDXL to generate high-quality horror centric images. It's an all-in-one model replacing my old 1.5 models Monster Diffusion, Creepy Diffusion and Evil Clown.This model is good for:Gore, monsters, creatures and realism.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/71ef0d0c-d975-47fe-9a7e-6612bdc4d10e/width=525/71ef0d0c-d975-47fe-9a7e-6612bdc4d10e.jpeg" />Happy prompting

Monster Diffusion SDXL

monsterDiffusionSDXL_sdV21Version.safetensors

monsterDiffusionSDXL_sdV21Version.yaml

SD v2.1 version

v1.0 SDXL

A 2.1-768 model that specializes in making baby versions of characters. All the pictures used as examples were generated with the prompt format *Angle* shot of (SmolOne:1.2) baby *character*, tiny *character*, intricate, highly detailed, digital painting, artstation, matte, sharp Tested mainly with the above prompt, the important thing is the SmolOne token from slight testing in other prompt formats. Training images were scraped from @tophmagoph_ on instagram. An artist who makes similar images using midjourney AI. Poorly captioned training images are attached for any use. There is a TI that goes well and was trained on this model called SmolGuysExample pictures include, in this order 1. Daredevil 2. Wonder Woman 3. One Punch Man 4. Naruto 5. Emma Watson 6. Afro Samurai 7. Elsa 8. Rick Sanchez 9. Ratchet 10. Rick Ross 11. Loki

SmolOnes

smolones_V1.safetensors

smolones_V1.yaml

smolones_V1_trainingData.zip

SmolOnes-v1

A bit more expressive and detailed than 1.0.

furrender_20.safetensors

furrender_20.yaml

<h1>Higher quality 2.1 images!</h1>Thank you for checking out the new and improved digital diffusion! This model is a general purpose 2.1 model that does well in many styles and themes. I really hope you enjoy the model, and please share what you can create with it!<h3>Basic prompting guide:</h3>This model might prompt closer to SD 1.5, since you don't need overly complicated prompts to get really cool images. The two most important tokens are digital art and photograph. These control what kind of image you are generating. It's pretty self explanatory what they do as well. There are other tokens that can improve your images or make them feel a certain way, or are just fun to experiment with. Here are some of my favorites!<ul><li>Portrait</li><li>Landcsape</li><li>Vehicle</li><li>Cinematic</li><li>Dramatic</li><li>Fantasy</li><li>Particles</li><li>Steampunk</li><li>Moody</li><li>Dark</li><li>Bright</li><li>Calm</li><li>Sunrise</li></ul>FOR V1:<a target="_blank" rel="ugc" href="https://docs.google.com/document/d/e/2PACX-1vRQwQYQtz2Y_rkxgFQUnhW8qgP2JS9L042eMxkMDJVP1hbkjDdk_KkBexUUXeR1d4mfQXecVhMf9sw9/pub"> the prompting guide </a>to better understand how to use the model to it's fullest extent, or at least to the extent I have discovered.

Digital Diffusion

IMPROVED PHOTOREALISM - I overhauled the dataset by removing 100 images, and adding 150 more, bringing the total to 300 images. I captioned all photography with the tag "photograph" and all digital art with the tag "digital art". Now can do professional like photography as well as digital art, both very well!Trained on top of v1.

Files with SHA256: f5a297b5bb166fb713cc0889a878fe66f86e38c62fc794cf13cdf0786ee8c127