<h2 id="heading-705">Description</h2>(for best results, read the full description - usage guide below)This is a merge of some random anime based and cartoon based models to achieve a somewhat cartoony anime style, more similar to what you would actually see in anime as opposed to the more common hyper-detailed anime models.Versions 3, 4, and 4.5 include some custom training to further enhance the style. More details available in "About this Version" on the sidebar. Most positive prompts for the v3 sample images were randomly generated.<h2 id="heading-706">Usage Guide</h2><ul><li>(highly recommended) Use a negative embedding for best results<ul><li>I use verybadimagenegative_v1.3 (all examples use this)</li><li>verybadimagenegative_v1.3<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/11772/verybadimagenegative">https://civarchive.com/models/11772/verybadimagenegative</a></li></ul></li><li>Place the downloaded file into the "embeddings" folder of the SD WebUI</li><li>In the negative prompt, paste "verybadimagenegative_v1.3"</li></ul></li><li>(highly recommended) Upscaling at 2x (or more) is important to getting a good result. I would recommend the following settings:<ul><li>Denoising strength of 0.45</li><li>Use the "R-ESRGAN 4x+ Anime6B" upscaler for a flatter look, or use "Latent" for a bit more detail</li><li>Leave hires steps at default of 0 (equal to your generation steps)</li></ul></li><li>(highly recommended) Use DPM++2M Karas as the sampler. Other samplers can yield odd artifacts, though your mileage may vary depending on your specific setup.</li><li>(only for version 3 and below) Use the dynamic thresholding plugin (all example images do with cfg scale 10 mimic 7): <a target="_blank" rel="ugc" href="https://github.com/mcmonkeyprojects/sd-dynamic-thresholding">https://github.com/mcmonkeyprojects/sd-dynamic-thresholding</a><ul><li>Set the CFG scale to 10.0</li><li>Click the checkbox "Enable Dynamic Thresholding (CFG Scale Fix)"</li><li>Set the Mimic CFG Scale to 7</li><li>If you don't want to use this plugin, then set the config scale to 5 or 6</li></ul></li><li>This model is very easy to prompt, and does not require a ton of prompt engineering to get good results. The following format will yield decent results:<ul><li>Prompt:<ul><li>(best-quality:0.8), perfect anime illustration, &lt;normal description of the image, e.g. a woman running in tokyo at night, a flaming meteor, etc.&gt;</li></ul></li><li>Negative:<ul><li>(worst quality:0.8), verybadimagenegative_v1.3, (surreal:0.8), (modernism:0.8), (art deco:0.8), (art nouveau:0.8)</li></ul></li></ul></li><li>The model is capable of NSFW</li></ul>

Flat-2D Animerge

This is a sharper version of v4.0, designed to have a cleaner look. It will follow prompts better than v4.0, along with providing higher saturation.

flat2DAnimerge_v45Sharp.safetensors

v4.5-sharp

v4.0-inpainting

v4.0

v3.0

v2.0

v1.0

TEST

test_v10.safetensors

Created by bigbeanboilerDescriptionThis is a merge of some random anime based and cartoon based models to achieve a somewhat cartoony anime style, more similar to what you would actually see in anime as opposed to the more common hyper-detailed anime models.Version 3 includes some custom training to further enhance the style. More details available in "About this Version" on the sidebar. Most positive prompts for the v3 sample images were randomly generated.Version 4 has a softer style that no longer needs the Dynamic Thresholding plugin for best results.Usage Guide<ul><li>(highly recommended) Use a negative embedding for best results<ul><li>I use verybadimagenegative_v1.3 (all examples use this)</li><li>verybadimagenegative_v1.3<ul><li><a target="_blank" rel="ugc" href="https://civitai.com/models/11772/verybadimagenegative">https://civitai.com/models/11772/verybadimagenegative</a></li></ul></li><li>Place the downloaded file into the "embeddings" folder of the SD WebUI</li><li>In the negative prompt, paste "verybadimagenegative_v1.3"</li></ul></li><li>(highly recommended) Upscaling at 2x or 2.5x using R-ESRGAN 4x+ Anime6B works very well (no need for high weights, 0.45 will work fine). Additionally, generating the pre-upscaled image at a higher resolution such as 768x768 will improve quality a lot.</li><li>(only for version 3 and below) Use the dynamic thresholding plugin (all example images do with cfg scale 10 mimic 7): <a target="_blank" rel="ugc" href="https://github.com/mcmonkeyprojects/sd-dynamic-thresholding">https://github.com/mcmonkeyprojects/sd-dynamic-thresholding</a><ul><li>Set the CFG scale to 10.0</li><li>Click the checkbox "Enable Dynamic Thresholding (CFG Scale Fix)"</li><li>Set the Mimic CFG Scale to 7</li><li>If you don't want to use this plugin, then set the config scale to 5 or 6</li></ul></li><li>This model is very easy to prompt, and does not require a ton of prompt engineering to get good results. The following format will yield decent results:<ul><li>Prompt:<ul><li>(best-quality:0.8), perfect anime illustration, &lt;normal description of the image, e.g. a woman running in tokyo at night, a flaming meteor, etc.&gt;</li></ul></li><li>Negative:<ul><li>(worst quality:0.8), verybadimagenegative_v1.3, (surreal:0.8), (modernism:0.8), (art deco:0.8), (art nouveau:0.8)</li></ul></li></ul></li><li>The model is capable of NSFW</li></ul>

flat2d-animerge

The original author of this model is bigbeanboiler. Shakker is committed to promoting the sharing and exchange of original models, so it has reprinted the model for everyone's non-commercial communication, learning and use. Users who use this model are asked to abide by the license stated by the original author.<h2 id="heading-705">Description</h2>(for best results, read the full description - usage guide below)This is a merge of some random anime based and cartoon based models to achieve a somewhat cartoony anime style, more similar to what you would actually see in anime as opposed to the more common hyper-detailed anime models.Versions 3, 4, and 4.5 include some custom training to further enhance the style. More details available in "About this Version" on the sidebar. Most positive prompts for the v3 sample images were randomly generated.<h2 id="heading-706">Usage Guide</h2><ul><li>(highly recommended) Use a negative embedding for best results<ul><li>I use verybadimagenegative_v1.3 (all examples use this)</li><li>verybadimagenegative_v1.3<ul><li><a target="_blank" rel="ugc" href="https://civitai.com/models/11772/verybadimagenegative">https://civitai.com/models/11772/verybadimagenegative</a></li></ul></li><li>Place the downloaded file into the "embeddings" folder of the SD WebUI</li><li>In the negative prompt, paste "verybadimagenegative_v1.3"</li></ul></li><li>(highly recommended) Upscaling at 2x (or more) is important to getting a good result. I would recommend the following settings:<ul><li>Denoising strength of 0.45</li><li>Use the "R-ESRGAN 4x+ Anime6B" upscaler for a flatter look, or use "Latent" for a bit more detail</li><li>Leave hires steps at default of 0 (equal to your generation steps)</li></ul></li><li>(highly recommended) Use DPM++2M Karas as the sampler. Other samplers can yield odd artifacts, though your mileage may vary depending on your specific setup.</li><li>(only for version 3 and below) Use the dynamic thresholding plugin (all example images do with cfg scale 10 mimic 7): <a target="_blank" rel="ugc" href="https://github.com/mcmonkeyprojects/sd-dynamic-thresholding">https://github.com/mcmonkeyprojects/sd-dynamic-thresholding</a><ul><li>Set the CFG scale to 10.0</li><li>Click the checkbox "Enable Dynamic Thresholding (CFG Scale Fix)"</li><li>Set the Mimic CFG Scale to 7</li><li>If you don't want to use this plugin, then set the config scale to 5 or 6</li></ul></li><li>This model is very easy to prompt, and does not require a ton of prompt engineering to get good results. The following format will yield decent results:<ul><li>Prompt:<ul><li>(best-quality:0.8), perfect anime illustration, &lt;normal description of the image, e.g. a woman running in tokyo at night, a flaming meteor, etc.&gt;</li></ul></li><li>Negative:<ul><li>(worst quality:0.8), verybadimagenegative_v1.3, (surreal:0.8), (modernism:0.8), (art deco:0.8), (art nouveau:0.8)</li></ul></li></ul></li><li>The model is capable of NSFW</li></ul>This is a sharper version of v4.0, designed to have a cleaner look. It will follow prompts better than v4.0, along with providing higher saturation.

Files with SHA256: fe95063ba60bc9298d60eb252f98d057039d9a882158afe042f266bdc1b1e528