<h1 id="stabilizer"><s>Stabilizer</s></h1>Name is misleading. This is NOT a LoRA that can magically fix your overfitted merged base model.This is a finetuned model from pretrained model. But trained as a LoRA.<ul><li>11k images. No bias, no default style.</li><li>Zero smooth plastic glossy AI image in dataset. Glossy Al images are polluting the world, but not on my watch, I handpicked every single image.</li><li>Natural language captions from Gemini, rather than tags in random order with high FPR.</li><li>Standard noise scheduler. Inpainting/img2img friendly.</li></ul>Improvements:You can get the style exactly as it should be (as long as the model knows).Comparisons with pretrained base model:<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/images/84145167">https://civarchive.com/images/84145167</a> (general styles, you get the style exactly as it should be)</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/images/84256995">https://civarchive.com/images/84256995</a> (artist styles, no style shifting because this model does not have bias)</li></ul>See more xy plots in cover images.Why LoRA?<ul><li>This LoRA is a <a target="_blank" rel="ugc" href="https://developer.nvidia.com/blog/introducing-dora-a-high-performing-alternative-to-lora-for-fine-tuning/">DoRA</a> (from Nvidia), which is more efficient than traditional LoRA.</li><li>Enough for thousands of training images.</li><li>What? You prefer to download and store a 7GiB checkpoint than a 80Mib LoRA?</li></ul>Share merges using this model is prohibited. FYI, there are hidden trigger words to print invisible watermark. I coded the watermark and detector myself. I don't want to use it, but I can.This model only published on Civitiai and TensorArt. If you see "me" and this sentence in other platforms, all those are fake and the platform you are using is a pirate platform.<hr /><h2 id="how-to-use">How to use</h2>It is highly recommended that you use pretrained base model.And load this LoRA with strength 1.Versions:<ul><li>cknb (<a target="_blank" rel="ugc" href="https://civarchive.com/models/2167995">ChenkinNoob-XL</a>).</li><li>nbvp10 (<a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1190596">NoobAI v-pred v1.0</a>). FYI: you don't need CFG hacks (RescaleCFG etc.).</li><li>nbep10 (<a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1116447">NoobAI eps v1.0</a>).</li><li>illus01 (Illustrious v0.1).</li></ul>Load this LoRA firstThis LoRA uses a new arch called <a target="_blank" rel="ugc" href="https://developer.nvidia.com/blog/introducing-dora-a-high-performing-alternative-to-lora-for-fine-tuning/">DoRA</a> from Nvidia, more efficient than traditional LoRA. But the patch weight is dynamically calculated based on the currently loaded base model weights (which will be changed when you loading other LoRAs). To avoid unexpected changes, load this LoRA first.Specify styles in promptThis model does not have an strong default style and is very creative. You must specify the style you want in the prompt.<hr />If you want to use it on finetuned/merged base models:I personally disagree this. This is not the model's original intention. But this is a LoRA after all.Be aware:This LoRA can't remove glossy shiny plastic AI style. Although the dataset is "AI image free". It can't make AI image polluted 1girl overfitted 50 versions of Nova furry 3D anime WAI or whatever look better. What the model learned is learned. Use a pretrained base model if you want to get rid of overfitted AI style.What is "overfitted AI style"? This is what Craft Lawrence (from spice and wolf) should be, if you've seen the anime: <a target="_blank" rel="ugc" href="https://civarchive.com/images/107381516">img</a>. This is what those AI style polluted 1girl overfitted model generated: <a target="_blank" rel="ugc" href="https://civarchive.com/images/107647042">img</a>Some base models already merged this model. If you got deformed images with this LoRA even at low strength (e.g. &lt;0.5). Your base model has already merged this LoRA (and you merged it twice). And the model weights got multiplied (because how the <a target="_blank" rel="ugc" href="https://developer.nvidia.com/blog/introducing-dora-a-high-performing-alternative-to-lora-for-fine-tuning/">DoRA</a> works) and collapsed.Beware of fake base model creators, aka. thieves. Some "creators" never do the training, they only grab other people's models, merge them, wipe all metadata and credits, and sell it as their own base model.<hr /><h2 id="update-log">Update log</h2>Moved <a target="_blank" rel="ugc" href="https://civarchive.com/articles/22251">here</a>

Stabilizer IL/NAI/CK

illustriousXLv01_stabilizer_v1.198.safetensors

Stabilizer IL/NAI

illus01 v1.198

cknb02 v0.304a

cknb02 v0.299a

nbvpred10 v0.280a

nbep10 v0.273

nbvpred10 v0.271

nbvped10 v0.264

illus01 v1.185c

illus01 v1.165c

illus01 v1.164

illus01 v1.152

nbep11 v0.205

nbep11 v0.198

nbep11 v0.178

illus01 v1.121

illus11 v1.113

illus01 v1.93

nbep11 v0.160

illus01 v1.72

illus01 v1.23

ani40 v0.1

nbep11 v0.138

nbep11 v0.129 (bad)

nbep11 v0.114

nbep11 v0.96

illus v1.7

nbep11 v0.58

nbep11 v0.30

nbep11 v0.11

illus v1.3

nbep10 v0.10

illus v1.0

This is my finetuned base model, but in a LoRA.This finetuned base model:<ul><li>Focus on creativity, rather than a fixed style. The dataset is very diverse. So this model does not have default style (bias) that limits its creativity.</li><li>Less deformed images. More logical. Should fix the problem of overfitting in pretrained anime base models. See "Why and how this works" section below.</li><li>Only natural textures, lighting, details. I handpicked every images in the dataset. Zero AI image. No smooth plastic AI style (No same AI faces. No plastic hair, smooth surfaces, etc...).</li><li>Better prompt comprehension. Trained with natural language captions.</li></ul>---------------Why there is no default style?<ul><li>What is "default style": If a model has a default style (bias), it means no matter what you prompted, the model must generate the same things (faces, backgrounds, feelings) that make up the default style.</li><li>Pros: It is easy to use, you won't have to prompt style anymore.</li><li>Cons: But you can not overwrite it either. If you prompt something that does not fit the default style, the model will just ignore it. If you stack more styles, the default style will always overlap/pollute/limit other styles.</li><li>"no default style" means you must add style (by tags or LoRAs). But when you stack more style tags/LoRAs, no style overlapping/pollution from this model. You can get the style you stacked exactly as it should be.</li></ul>--------------------Why is this "finetuned base model" a LoRA?<ul><li>I'm not a gigachad and don't have millions of training images. Finetuning the whole base model is not necessary, a LoRA is enough.</li><li>I can save tons of VRAM so I can use bigger batch size.</li><li>I only have to upload, and you only need to download, a tiny 40MiB file, instead of a 7GiB big fat checkpoint, which can save 99.4% data and storage. <s>So I can spam update it</s>.</li><li>This LoRA may seem small, it is still powerful. Because it uses a new arch called from Nvidia, which is more efficient than traditional LoRA.</li></ul>----------------------Then how can I get the "finetuned base model"?Simple.pretrained base model + This LoRA = the "finetuned base model"Just load this LoRA on the pretrained base model with full strength. Then the pretrained base model will become the finetuned base model.Two ways to use this model:1). Use it as a finetuned base model (Recommended):If you want the finest and natural details and build the style combination you want, with full control.Just load this LoRA first on the pretrained base model with full strength. Then the pretrained base model will become to the finetuned base model.2). Use it as a LoRA on other base model.Because why not, it's a LoRA after all.But beware, this is not a style LoRA.You are about to merge two base models. Simply add this LoRA to your base model usually won't give you what you expected. You may need to balance other weights (LoRAs, U-net blocks, etc.)....--------------See full description here: https://civitai.com/models/971952 .The model pages here are a little bit messy because they were duped or faked by other accounts, and were reclaimed to my account by site mod. At a least all versions are runnable now.If you see the duplicated warning, just click the "View duplicate model", this will lead you to the page that has a clickable "run" button.If you want to bookmark the model, bookmark this page. Other duplicated pages will be removed in the future.

nbvp10 v0.271

This is my finetuned base model, but in a LoRA.This finetuned base model:<ul><li>Focus on creativity, rather than a fixed style. The dataset is very diverse. So this model does not have default style (bias) that limits its creativity.</li><li>Less deformed images. More logical. Should fix the problem of overfitting in pretrained anime base models. See "Why and how this works" section below.</li><li>Only natural textures, lighting, details. I handpicked every images in the dataset. Zero AI image. No smooth plastic AI style (No same AI faces. No plastic hair, smooth surfaces, etc...).</li><li>Better prompt comprehension. Trained with natural language captions.</li></ul>---------------Why there is no default style?<ul><li>What is "default style": If a model has a default style (bias), it means no matter what you prompted, the model must generate the same things (faces, backgrounds, feelings) that make up the default style.</li><li>Pros: It is easy to use, you won't have to prompt style anymore.</li><li>Cons: But you can not overwrite it either. If you prompt something that does not fit the default style, the model will just ignore it. If you stack more styles, the default style will always overlap/pollute/limit other styles.</li><li>"no default style" means you must add style (by tags or LoRAs). But when you stack more style tags/LoRAs, no style overlapping/pollution from this model. You can get the style you stacked exactly as it should be.</li></ul>--------------------Why is this "finetuned base model" a LoRA?<ul><li>I'm not a gigachad and don't have millions of training images. Finetuning the whole base model is not necessary, a LoRA is enough.</li><li>I can save tons of VRAM so I can use bigger batch size.</li><li>I only have to upload, and you only need to download, a tiny 40MiB file, instead of a 7GiB big fat checkpoint, which can save 99.4% data and storage. <s>So I can spam update it</s>.</li><li>This LoRA may seem small, it is still powerful. Because it uses a new arch called from Nvidia, which is more efficient than traditional LoRA.</li></ul>----------------------Then how can I get the "finetuned base model"?Simple.pretrained base model + This LoRA = the "finetuned base model"Just load this LoRA on the pretrained base model with full strength. Then the pretrained base model will become the finetuned base model.----------------------Latest versions:<ul><li>nbvp10 v0.271 (for <a target="_blank" rel="ugc" href="https://civitai.com/models/833294?modelVersionId=1190596">NoobAI v-pred v1.0</a>). Accurate colors and finest details. This is the best model so far. Note that: It is a v-pred LoRA. It does NOT work on eps models.</li><li>nbep10 v0.273 (for <a target="_blank" rel="ugc" href="https://civitai.com/models/833294?modelVersionId=1116447">NoobAI eps v1.0</a>). Discontinued. Less saturation and contrast comparing to v-pred models. Due to a "small design flaw" in standard epsilon (eps) prediction. It limits the model reaching broader color range. That's why we have v-pred later.</li><li>illus01 v1.198 (for Illustrious v0.1). Discontinued. Just too old...</li></ul>-------------------Two ways to use this model:1). Use it as a finetuned base model (Recommended):If you want the finest and natural details and build the style combination you want, with full control.Just load this LoRA first on the pretrained base model with full strength. Then the pretrained base model will become to the finetuned base model.2). Use it as a LoRA on other base model.Because why not, it's a LoRA after all.But beware, this is not a style LoRA.You are about to merge two base models. Simply add this LoRA to your base model usually won't give you what you expected. You may need to balance other weights (LoRAs, U-net blocks, etc.)....--------------See full description here: https://civitai.com/models/971952 .The model pages here are a little bit messy because they were duped or faked by other accounts, and were reclaimed to my account by site mod. At a least all versions are runnable now.If you see the duplicated warning, just click the "View duplicate model", this will lead you to the page that has a clickable "run" button.If you want to bookmark the model, bookmark this page. Other duplicated pages will be removed in the future.

Files with SHA256: c502b406ef9bf74c924637d50d606a13d9bfe2362c00e8b4ba00440ef64acf22