<h2 id="2dn-illust-v2.0">2DN-Illust v2.0</h2>Currently, my best model! It includes training information from realistic gens, anime and fantasy, and allows you to mix all of those! Works perfectly well with Illustrious and NoobAI (NAI) LoRAs, allowing you to leverage data other models don't have. IMPORTANT INFORMATION:<ul><li>For reasons, the model is biased toward teal/green tints, especially for realism, use "green theme" in your negative prompt to remove this green look.</li><li>For landscapes and backgrounds, use around 35-50 HIRES steps.</li><li>Look at the metadata, the little (i) icon on the preview images to learn about the prompts and settings I used. I use reForge. </li><li>Avoid using expression prompts like "smile" in realistic images, it will use the anime data and give you something incredibly creepy. Use (smile:0.1) etc to weaken the creepy effect. </li></ul><h2 id="2dn-nai-v2.0-yang">2DN-NAI v2.0 YANG阳</h2>Just as detailed as v2.0 YIN阴, but creamier, gentler and brighter. What I mean to say is: it's not as bonkers on contrast and SD1.5-like compositions, but it still packs a punch. For reference ALL of the preview images have the same settings, prompt and seed as the 阴versions, so you can compare them directly. And also, it's way way more creative as a model, expect surprises, pleasant ones! It also responds much better to LoRAs, meaning you can go ham with style and character models. It may seem a bit pale, but you can control this with various style LoRAs really well.<h2 id="2dn-nai-v2.0-yin">2DN-NAI v2.0 YIN阴</h2>My best realistic model now goes a bit HARDER! See previous version for description. None of the preview images use ADetailer, the model does it's best to make details happen. Use minimal steps for reasonable results (higher step counts will produce high contrast). Overall, this model is: very fast, sharp and great for vibrant gens using NoobAI tags.Carried by an asian/anime aesthetic, it excels at NSFW gens - essentially stuff you can't get easily with ChatGPT/Gemini.<h2 id="2dn-anime-v3.0">2DN-ANIME v3.0</h2>2026 Edition released<h2 id="2dn-anime-v2.0">2DN-ANIME v2.0</h2>Major improvements:<ol><li>Prompt obedience</li><li>Prompt adhesion between seeds</li><li>More balanced contrast and details [increase CFG scale to increase contrast, if samples look too subtle to you]</li><li>Better anatomy</li><li>More concepts</li><li>OneShotFacial technology integrated, which means you don't need to use ADetailer/etc</li><li>More detailed backgrounds</li><li>Better expressions</li><li>More accurate artist styles</li><li>Better composition</li><li>Less latent garbling</li><li>Better character-to-character interaction support</li><li>Finer textures</li><li>More balanced landscapes</li><li>Better LoRA support (will not burn as easily with many LoRA's applied)</li></ol>I recommend an img2img pass at the end with the same settings, sometimes with 50% of the original CFG scale (e.g. to avoid toe multiplication)This is a hybrid v-pred checkpoint so you may need to hunt around for the best CFG scale to use with your image gen software.All but 3 sample images were chosen from the first generation that ran. The 3 needed between 3 and 5 retries.Samples generated with reForge -- you may need to adjust the settings in other software.<h2 id="2dn-anime-v1.0">2DN-ANIME v1.0</h2>Due to popular demand, I've decided to upload a "flat" anime version of 2DN, that retains the model knowledge and detail of the semi-real models. It is much easier to use and doesn't require exotic samplers or schedulers and will work with Euler A.This model is actually great for creating game CG assets! So the previews are all wide-screen. If I've stolen your prompt, my apologies, I am a thief who likes your work.Some software (such as the CivitAI generator) like settings like this:CFGSCALE: 5STEPS: 29SAMPLER: EULER AI use reForge with:CFGSCALE:1STEPS:29SAMPLER: Euler Ancestral CFG++SCHEDULER: SGM UniformFor comfyUI steal the settings or workflows from anyone kind enough to post their metadata. comfyUI confuses the heck out of me so unfortunately I can't help there.For reasons unknown to me ADetailer fixes feet really well with this model (as in it actually removes extra toes). I just use the hand model, and most of the time it thinks feet are hands, so it catches them.Please try using the model first without stacking LoRAs like crazy on it. It already has my NAI v-pred fix integrated - so chances are some detail LoRAs will fry the outputs. You can easily prompt for different styles using booru artist tags/combos.<h2 id="2dn-nai-v1.0">2DN-NAI v1.0</h2>This is my best general-purpose model! All of the sample images have the same seed! They were not cherry picked!I wanted to make a model that leveraged the sheer creativity and knowledge of NoobAI (NAI) v-pred v1.0 - so after much "hitting head on brick wall" here it is!The culmination of all of the 2DN series model vision - a highly detailed model that lets you do anime, realism, slop, or fancy art, with the ability to produce striking images thanks to v-pred.Sample metadata:<pre><code>masterpiece, very aesthetic, best quality, newest, absurdres, highres, very awa,
BREAK
1girl, solo, colorful, glowing, eyes, realistic, bodysuit, safe

Negative prompt: lowres, worst quality, low quality, bad anatomy, bad hands, multiple views, abstract, signature, furry, anthro, 2koma, 4koma, comic, manga, text, watermark, username, artist signature, patreon logo, patreon username, twitter username,

Steps: 14, 
Sampler: DPM++ SDE CFG++, 
Schedule type: SGM Uniform, [using reForge]

CFG scale: 2, 
Seed: 3493447269, 
Size: 832x1216, 
Model hash: 565548f2eb,

Denoising strength: 0.2, 
Hires CFG Scale: 2, Hires upscale: 1.5, Hires steps: 20,
Hires upscaler: R-ESRGAN 4x+ Anime6B,

Token merging ratio: 0.5, Token merging ratio hr: 0.5, 

ADetailer model: face_yolov8n.pt, ADetailer confidence: 0.3, ADetailer dilate erode: 4, ADetailer mask blur: 17, ADetailer denoising strength: 0.2, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer use inpaint width height: True, ADetailer inpaint width: 1024, ADetailer inpaint height: 1024, ADetailer use separate steps: True, ADetailer steps: 60, ADetailer model 2nd: hand_yolov8n.pt, ADetailer confidence 2nd: 0.3, ADetailer dilate erode 2nd: 4, ADetailer mask blur 2nd: 4, ADetailer denoising strength 2nd: 0.4, ADetailer inpaint only masked 2nd: True, ADetailer inpaint padding 2nd: 32, ADetailer version: 25.3.0

Hierarchical CLIP Within Boost: 1, ["off", doesn't affect the images, I'm working on a fork of reForge with hierarchal prompting which is not used here]</code></pre><h2 id="2dn-latentlens-v2.0">2DN-LatentLens v2.0</h2>Improvements to model fidelity and knowledge. Difficult to use.<pre><code>Checkpoint note: if you're getting bad anatomy and warped results, turn down the denoising in your hiresfix pipeline and/or reduce the number of steps. Weird faces? Turn down the denoising in ADetailer. The model is designed to give you details, and can be more aggressive than other models. Closeups messing up? Turn off ADetailer altogether!</code></pre><h2 id="2dn-latentlens-v1.0">2DN-LatentLens v1.0</h2>It uses the right sampler and scheduler settings not available on CivitAI or any other online image generator service. It is also very fast.Introducing 2DN LatentLens.LatentLens is a v-pred model, based on NoobAI XL v-pred v1.0It uses a novel technique called LatentLens, which increases model responsiveness to prompts, coherence and quality. For example, most of the preview images use neither hires fix, face detailers nor upscaling. LatenLens makes models more flexible, allowing you to explore various creative prompting strategies while seeing consistently coherent and vibrant generation results.This model works with NoobAI artist tags (not pictured) and is good at explicit content (not pictured).My intention when working on this model was to "let people's dreams come true easily".For best results:Include in positive prompt:<pre><code>masterpiece, best quality, amazing quality, very aesthetic, absurdres, very awa,</code></pre>Include in negative prompt:<pre><code>lowres, worst quality, low quality, bad anatomy, bad hands, multiple views, abstract, signature, furry, anthro, 2koma, 4koma, comic, manga, text, logo, artist signature, patreon logo, patreon username, twitter username</code></pre>Recommended settings:Guidance: 1.1Steps: 20Sampler: DPM++ SDE CFG++Scheduler: SGM UniformSoftware: reForgeThe model is also available on <a target="_blank" rel="ugc" href="https://tensor.art/models/851584206017440111/2DN-LatentLens-v1">TensorArt</a><h2 id="2dn-illust-v1.0">2DN-Illust v1.0</h2>Introducing 2DN Illustrious.This model uses IllustriousXL/NoobAI as a base. It was fine-tuned using 65,000 high quality photos for 12 epochs, two of which were preconditioning. Note that I specifically avoided training on cosplay photos and selected a very diverse dataset (LAION etc). It was further refined with custom LORAs (such as my cfg scale LoRA).For those of you coming from Pony there are some important things to note:<ul><li>Your Pony LoRAs won't work. This is not as big of an issue as you might imagine. Illustrious/Noob has more than 100x the concepts and tags available for use than Pony. Including obscure tags you can only find on Danbooru. It also has tens of thousands of artist and characters tags if you want to make anime images or mix them into the realism style.</li><li>You don't need to use the pony score tags. They will only interfere with the images.</li></ul>REALISTIC MODEI recommend the following base prompt:<pre><code>highly detailed, realistic, fine fabric detail, absurdres, highly-detailed, best quality, masterpiece, very aesthetic, &lt;your prompt&gt;</code></pre>For the negative prompt you should almost always use:<pre><code>lowres, worst quality, low quality, bad anatomy, bad hands, multiple views, abstract, signature, furry, anthro, bkub, 2koma, 4koma, comic, manga, sketch, ixy,</code></pre>Inserting artist tags of creators who make highly non-realistic artworks such as ixy and bkub improves the quality of the outputs.Using artist names in the positive prompt will make the model produce anime style images. For a 2.5D look reduce the weight of the artist tags to 0.5 for example.Facial expression tags will result in exaggerated results. Lower the weight of these tags also to control their effect when generating realistic images.Lower CFG scale settings will produce less saturated images with lower contrast.You can control the temperature/colour cast of the images by specifying for example „warm light” in the positive prompt and „blue, blue light” in the negative prompt.If the model produces „babyface” during the ADetailer stage, set ADetailer positive prompt to an anime artist name such as „quasarcake”.ANIME MODESimply prompt as you would any illustrious model, including artist tags.—Highres-fix or upscaling is highly recommended (0.3 denoising strength works well). ADetailer is essential for non close-ups of subjects.Recommended CFG scale is 6.5. Adjust to taste.Training was performed on a RunPod A100 GPU, costing $200USD. The model will be buzz gated for a short while. Your money will go towards offsetting the training costs.<h2 id="2dn-pony-v2.0">2DN-Pony v2.0</h2>I'm happy to release v2.0 of the original 2DN-Pony series! The new model has many improvements across the board:<ul><li>Better anatomy</li><li>More pleasing and focused composition</li><li>Finer details</li><li>Wider dynamic range</li><li>Deep tonality the original model was known for</li><li>Works with a bigger range of CFG scales</li></ul>It is being released for a short time under the EA program to help support further development.Note the model is highly detailed, so you do not need to use detail/slider LoRAs to get fine structure in your images by default.<h2 id="2dn-pony-v1.0-nost">2DN-Pony v1.0 NoST</h2>As thanks for those who have donated buzz for early access PLaY I’m releasing NoST(algia). This 2DN version aims to replicate the feel of SD1.5 models, including ridiculous detail, sameface 😂, rich backgrounds, and too many mechs when you use the mecha token. Unfortunately (?) it’s surprisingly good at hands and fingers. Motivated in part because I looked back on my old SD1.5 gens and there was something fun and kooky about them that got lost along the way.<hr /><h2 id="announcing-2dn-pony-v1.0-play">Announcing 2DN-Pony v1.0 PLaY</h2>Update: site gen isn't really working for some reason, sorry!Merging reality with fantasy... Let your dreams run wild!My best model and biggest fine-tuning project to date.Trained on 70,000 selected photos.I used the buzz donated from 2DN ReAL and put it toward cloud GPU compute to fine-tune this model. Any donations on this model will 100% go towards training new models (after CivitAI's cut).Good for SFW, and NSFW. Pony Lora compatible but keep in mind this is a realistic model. An anime Lora won't always make the images anime-style but more often will change the gens in interesting ways (such as mood).More information on the model and usage tips coming soon...<hr /><h2 id="2dn-pony-v1.0-real">2DN-Pony v1.0 ReAL</h2>Update: ReAL is now in the site generatorUpdate: the ReAL version ups the realism, especially with the “realistic” tag. Now produces a wide variety of images. It is being released under early access. Buzz will go towards training on a large realistic dataset. Big thank you to everyone who is dropping buzz on this model ❤️The ReAL version is seed-matched with v1 - meaning you can try regenerating your v1 images with the same settings + seed and the general appearance should be similar in terms of content and composition.Motivated by not being able to do certain stuff in Flux. I actually prefer promoting with booru tags as well, instead of long natural language prompts. I think the Pony base model is still unmatched.Original description:See sample images for prompt ideas. The model can produce anime to 80% realistic content.If you are after a fully realistic Pony model I recommend <a target="_blank" rel="ugc" href="https://civarchive.com/models/476745?modelVersionId=530243">Godiva</a>. For a 2D anime model, check out <a target="_blank" rel="ugc" href="https://civarchive.com/models/484571?modelVersionId=538906">CashMoney</a>.Update: Works with onsite image generator!Thank you to Pony Diffusion team for the game-changing Pony base model.

2dn_ponyV1.safetensors

Pony-v1

Illust-v2

NAI-v2-YANG阳

NAI-v2-YIN阴

ANIME-v3

ANIME-v2

ANIME-v1

NAI-v1

LatentLens-v2

LatentLens-v1

Illust-v1

Pony-v2

Pony-v1 NoST

Pony-v1 PLaY

Pony-v1 ReAL

Files with SHA256: c85b8558ed29c11b9d8330edcdcc30da348fab8f05e2e54466be50cf91abe26e