Hassaku aims to be a anime model with a bright and distinct anime style.My <a target="_blank" rel="ugc" href="https://discord.gg/zSR5FcYWWE">Discord</a> for everything related to anime models and art. If you'd like to support my work, you can do so at: <a target="_new" rel="ugc" href="https://subscribestar.adult/citrus-models">SubscribeStar</a>, every bit helps and is truly appreciated! ____________________________________________________________ Supporters:Thanks to my supporters tamashiicolle, pttcot, SETI and Kodokuna ____________________________________________________________ Using the model:<ul><li>The model was trained primarily on images with minimal disruptive elements, such as floating text, logos, speech bubbles, or signatures. If any of these elements appear in an image, please include "signature" in your negative prompt.</li><li>Danbooru <a target="_blank" rel="ugc" href="https://danbooru.donmai.us/wiki_pages/tag_group%3Ametatags">Metadata</a> and franchise tags are not used in training, so please avoid using them in prompts. Metadata such as "highres" and franchise tags like "re:zero kara hajimeru isekai seikatsu" are not used in training.</li><li>A CFG scale between 3 and 7 is recommended. For best results, use CFG 6 with the Euler a sampler.</li><li>Refer to the example images, to understand, how the model should be used.</li><li>The model is designed to be simple and straightforward to prompt. Use the following tag order:<ol><li>Number of characters</li><li>Character Tags</li><li>All remaining tags Example: 1girl, rem \(re:zero\), standing, masterpiece, upper body</li></ol></li><li>Here are some resolution options for SDXL:<ul><li>1536 x 640</li><li>1344 x 768</li><li>1216 x 832</li><li>1152 x 896</li><li>1024 x 1024</li><li>896 x 1152</li><li>832 x 1216 (most recommended)</li><li>768 x 1344</li><li>640 x 1536</li></ul></li></ul>Lora use:<ul><li>NoobAIs Loras working for the most part better in compare to <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">Illustrious loras</a></li><li>Versions 2 and 3 is less compatible to most loras trained on Illustrious or Noob, because it got further trained away of both. Style A is still the most compatible for it.</li></ul> ______________________________________________________Version and License info:<ul><li>Below V1 merges <a target="_blank" rel="ugc" href="https://civarchive.com/models/260267">ANIMAGINE XL 3.0</a></li><li>Version V1 use <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">Illustrious-XL</a> &amp;<a target="_blank" rel="ugc" href="https://civarchive.com/models/827184?modelVersionId=1068947"> WAI-illustrious-SDXL</a> with additional training</li><li>V2 is trained on its own and don't include any extra merge. Base was V1, it is trained to include newer or missing characters. It was also used for further training tests</li><li>V3 is a merge of <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">Illustrious-XL</a> and V2.2, to fix some issues and was also trained to include newer or missing charactersAll Models using the <a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a> license.</li></ul>

Hassaku XL (Illustrious)

Be aware that this is a WIP model, WIP means mostly the knowleghe of new characters, outsite of that, it is a full working model, but there is still work on it to do. The model occasionally performs better when using more than 75 tokens and it also creates a bit to detailed/realistic shiny/glossy bodys currently, both will change in a later update. Model is training on changing datasets, ranging from 120k to around 760k images. The primary learning dataset (70k images) included characters from the past year (01.06.2024 of last year to now), with at least 100 images on Danbooru. The learning dataset was heavily filtered by score and quality, compressing it to a relative small size of 70k images. Note: While the most recent characters from the last week are included, they are not yet trained well enough to be reliable (like Sameko Saba). In Detail: Over the past two months, I ran into several issues. After about two weeks of training, the model began to deteriorate rapidly for no apparent reason.As a result, I had to do one hard reset and two soft resets during the process, effectively throwing away a lot of time, effort, and money. I only discovered the root cause at the beginning of this month. So, this current version is still mid-training. It mainly includes faces and hairstyles of new characters, while clothing is still in the process to get learned for the most part. I'm sharing it now despite the state it's in, as I'm already 2 months over my schedule now.This model has a style merge, which can sometimes lead to artifacts on the eyes, especially viewed from a distance. This aligns what other models are doing.

hassakuWIPV3.safetensors

[Deprecated] Hassaku XL (Illustrious) - Ikena

v3 WIP

v3.4

v3.3

v3.2

v3_Base

v3.1

v2.2

v2.1fix

v2.1

v1.3 - Style B

v1.3 - Style A

v1.2 - Style

v1.1 - Style

V1.0 - Style

V1.0

beta V0.6

beta V0.4

beta V0.2M

beta V0.2

beta V0.1

alpha V0.9

alpha V0.8

alpha V0.7

alpha V0.6

alpha V0.5

alpha V0.4

alpha V0.3

alpha V0.2

alpha V0.1

Hassaku aims to be a anime model with a bright and distinct anime style. You can run Hassaku XL and use its API on SinkIn: <a target="_blank" rel="noopener noreferrer nofollow" href="https://sinkin.ai/m/JWknjgr">https://sinkin.ai/m/JWknjgr</a>My <a target="_blank" rel="ugc" href="https://discord.gg/zSR5FcYWWE">Discord</a> for everything related to anime models and art. You can support me on my <a target="_blank" rel="ugc" href="https://www.patreon.com/user?u=27247323">patreon</a>.____________________________________________________________ Supporters:Thanks to my supporters Riyu, SETI and Kodokuna on my <a target="_blank" rel="ugc" href="https://patreon.com/user?u=27247323&amp;utm_medium=clipboard_copy&amp;utm_source=copyLink&amp;utm_campaign=creatorshare_creator&amp;utm_content=join_link">patreon</a>!____________________________________________________________ Using the model:<ul><li>The model is trained using images with minimal disruptive elements such as floating text, logos, speech bubbles, and signatures. If any of these elements are present in an image, please include the prompt "signature" as a negative prompt</li><li>Metadata and franchise tags are excluded—please do not use them. Tags such as "highres" and franchise-related tags like "re:zero kara hajimeru isekai seikatsu" are not used in training</li><li>Look at the example images, to see how the model should be used</li><li>Model is trained to be not complicated in use, tag order: First are the number of person, then character names, rest. Example: 1girl, rem \(re:zero\), standing, masterpiece, upper body</li><li>Here are some resolution options for SDXL:<ul><li>1536 x 640</li><li>1344 x 768</li><li>1216 x 832</li><li>1152 x 896</li><li>1024 x 1024</li><li>896 x 1152</li><li>832 x 1216 (most recommended)</li><li>768 x 1344</li><li>640 x 1536</li></ul></li></ul>______________________________________________________Version and License info:<ul><li>Below V1 merges <a target="_blank" rel="ugc" href="https://civitai.com/models/260267">ANIMAGINE XL 3.0</a></li><li>Version V1 use <a target="_blank" rel="ugc" href="https://civitai.com/models/795765/illustrious-xl">Illustrious-XL</a> &amp;<a target="_blank" rel="ugc" href="https://civitai.com/models/827184?modelVersionId=1068947"> WAI-NSFW-illustrious-SDXL</a> with additional training</li><li>V2 is trained on its own and don't include any extra merge. Base was V1, it is trained to include newer or missing characters. It was also used for further training tests</li><li>V3 is a merge of <a target="_blank" rel="ugc" href="https://civitai.com/models/795765/illustrious-xl">Illustrious-XL</a> and V2, to fix some issues and was also trained to include newer or missing charactersAll Models using the <a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a> license.</li></ul>

hassakuXLIllustrious_v30.safetensors

Hassaku aims to be a anime model with a bright and distinct anime style.You can run Hassaku XL and use its API on SinkIn: <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://sinkin.ai/m/JWknjgr">https://sinkin.ai/m/JWknjgr</a>V1 use illustrious-xl as base, versions from 0.2M up are trainined with quality prompts like masterpiece or worst quality. Recommended prompts in negative are "worst quality, bad quality" and masterpiece in positiv. There is also my <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/376031/hassaku-xl-hentai">pony xl</a> variant.My <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://discord.gg/zSR5FcYWWE">Discord</a> for everything related to anime models and art. You can support me on my <a target="_blank" rel="noopener noreferrer nofollow" href="https://subscribestar.*****/citrus-models">subscribestar</a>.My models:<a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/2583"> hassaku,</a> <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/85909/sudachi">sudachi(flat 2d)</a>, <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/41916/koji">koji(2d)</a>, <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/67120/yuzu">yuzu(light semirealistic)</a>, <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/24383">grapefruit</a>_____________________________________________________Supporters:Thanks to my supporters Riyu, SETI and Kodokuna_____________________________________________________Using the model:<ul><li>Model is trained with images with minimal disruptive features like floating texts, logos, speak bubbles and signatures as possible. If such features appearing in a image, please use prompt "signature" as negative.</li><li>Excluded metadata and franchise tags, don't use them. meta data -&gt; something like "highres", franchise tags like "re:zero kara hajimeru isekai seikatsu" are pruned on characters like "rem_(re:zero)".</li><li>Here are some good resolution options for SDXL:<ul><li>1024 x 1024</li><li>1152 x 896</li><li>896 x 1152</li><li>1216 x 832</li><li>832 x 1216 (most recommended)</li><li>1344 x 768</li><li>768 x 1344</li><li>1536 x 640</li><li>640 x 1536</li></ul></li></ul>License info:Because it merges <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/260267">ANIMAGINE XL 3.0 </a>below version V1 and <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/795765/illustrious-xl">Illustrious-XL</a> &amp;<a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/827184?modelVersionId=1068947"> WAI-NSFW-illustrious-SDXL</a> beginning from V1: <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a>V2 is trained on its own and don't include any merge, just <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/795765/illustrious-xl">Illustrious-XL 0.1</a>, but trained to include newer or missing characters, which also use the <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a> license.

Be aware that this is a WIP model, WIP means mostly the knowleghe of new characters, outsite of that, it is a full working model, but there is still work on it to do.

The model occasionally performs better when using more than 75 tokens and it also creates a bit to detailed/realistic shiny/glossy bodys currently, both will change in a later update.

Model is training on changing datasets, ranging from 120k to around 760k images. The primary learning dataset (70k images) included characters from the past year (01.06.2024 of last year to now), with at least 100 images on Danbooru. The learning dataset was heavily filtered by score and quality, compressing it to a relative small size of 70k images. Note: While the most recent characters from the last week are included, they are not yet trained well enough to be reliable (like Sameko Saba).


In Detail:
Over the past two months, I ran into several issues. After about two weeks of training, the model began to deteriorate rapidly for no apparent reason.

As a result, I had to do one hard reset and two soft resets during the process, effectively throwing away a lot of time, effort, and money. I only discovered the root cause at the beginning of this month. So, this current version is still mid-training. It mainly includes faces and hairstyles of new characters, while clothing is still in the process to get learned for the most part. I'm sharing it now despite the state it's in, as I'm already 2 months over my schedule now.

This model has a style merge, which can sometimes lead to artifacts on the eyes, especially viewed from a distance. This aligns what other models are doing.

v3.0

Hassaku aims to be a anime model with a bright and distinct anime style.My <a target="_blank" rel="ugc" href="https://discord.gg/zSR5FcYWWE">Discord</a> for everything related to anime models and art. If you'd like to support my work, you can do so at: <a target="_new" rel="ugc" href="https://subscribestar.adult/citrus-models">SubscribeStar</a>, every bit helps and is truly appreciated! ____________________________________________________________ Supporters:Thanks to my supporters tamashiicolle, pttcot, SETI and Kodokuna ____________________________________________________________ Using the model:<ul><li>The model was trained primarily on images with minimal disruptive elements, such as floating text, logos, speech bubbles, or signatures. If any of these elements appear in an image, please include "signature" in your negative prompt.</li><li>Danbooru <a target="_blank" rel="ugc" href="https://danbooru.donmai.us/wiki_pages/tag_group%3Ametatags">Metadata</a> and franchise tags are not used in training, so please avoid using them in prompts. Metadata such as "highres" and franchise tags like "re:zero kara hajimeru isekai seikatsu" are not used in training.</li><li>A CFG scale between 3 and 7 is recommended. For best results, use CFG 6 with the Euler a sampler.</li><li>Refer to the example images, to understand, how the model should be used.</li><li>The model is designed to be simple and straightforward to prompt. Use the following tag order:<ol><li>Number of characters</li><li>Character Tags</li><li>All remaining tags Example: 1girl, rem \(re:zero\), standing, masterpiece, upper body</li></ol></li><li>Here are some resolution options for SDXL:<ul><li>1536 x 640</li><li>1344 x 768</li><li>1216 x 832</li><li>1152 x 896</li><li>1024 x 1024</li><li>896 x 1152</li><li>832 x 1216 (most recommended)</li><li>768 x 1344</li><li>640 x 1536</li></ul></li></ul>Lora use:<ul><li>NoobAIs Loras working for the most part better in compare to <a target="_blank" rel="ugc" href="https://civitai.com/models/795765/illustrious-xl">Illustrious loras</a></li><li>Versions 2 and 3 is less compatible to most loras trained on Illustrious or Noob, because it got further trained away of both. Style A is still the most compatible for it.</li></ul> ______________________________________________________Version and License info:<ul><li>Below V1 merges <a target="_blank" rel="ugc" href="https://civitai.com/models/260267">ANIMAGINE XL 3.0</a></li><li>Version V1 use <a target="_blank" rel="ugc" href="https://civitai.com/models/795765/illustrious-xl">Illustrious-XL</a> &amp;<a target="_blank" rel="ugc" href="https://civitai.com/models/827184?modelVersionId=1068947"> WAI-NSFW-illustrious-SDXL</a> with additional training</li><li>V2 is trained on its own and don't include any extra merge. Base was V1, it is trained to include newer or missing characters. It was also used for further training tests</li><li>V3 is a merge of <a target="_blank" rel="ugc" href="https://civitai.com/models/795765/illustrious-xl">Illustrious-XL</a> and V2.2, to fix some issues and was also trained to include newer or missing charactersAll Models using the <a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a> license.</li></ul>

hassakuXLIllustrious_v3WIP.safetensors

Files with SHA256: b4fb5f829a46a91f8499a2c7c0a0653c0e8de1632c0b03285a0495b0c068e888