In Norse mythology, Ratatoskr (Old Norse, generally considered to mean "drill-tooth" or "bore-tooth") is a squirrel who runs up and down the world tree Yggdrasil to carry messages between the eagle perched atop Yggdrasil and to the roots of the tree to Nidhogg.This model is for Animals / Creatures and Furries but can do way more :<h3 id="because-it's-an-flux-kontext-model-its-main-useis-image-to-image-keep-that-in-mind.">Because it's an Flux Kontext model its main use is image to image keep that in mind.</h3>This model can do:<ul><li>Photorealistic</li><li>Digital Art</li><li>Anime</li><li>Comic</li><li>Vector Graphics</li><li>Line art</li><li>Stickers</li><li>can write short text</li><li>furry</li><li>etc</li></ul>This is the Flux Kontext variant of <a target="_blank" rel="ugc" href="https://civarchive.com/models/681795/ratatoskr-animal-creature-and-furry-flux">Ratatoskr Flux </a>The use case is for example for editing any picture made with the ratatoskr model series you can find in my profile but its working with any given pictures too.<h3 id="changelog:">Changelog:</h3>V1: First Release Versionthis is a block merged model made with the Original Kontext Model, and Parts of <a target="_blank" rel="ugc" href="https://civarchive.com/models/681795/ratatoskr-animal-creature-and-furry-flux">Ratatoskr Flux</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/models/1636436/sleipnir-flux">Sleipnir Flux</a>Note: this is "Just" V1 and not directly trained on the Ratatoskr Dataset yet but i will use this block merge for the starting point for an actual finetune (V2) so there will for sure some Updates in the future.V2:This is the first trained Version that is using like i mentioned the V1 Block merged versionIts trained now at 175 paired images i created on the Ratatoskr Database. Because of the difference of captaining of kontext to my standard model database i did write all the caption by hand that alone took over 9 hours the training time itself did took some days...<ul><li>the training helped a lot to "repair the damage" of the block merge with the standard flux kontext model</li><li>way more consistent</li><li>better in sfw and nsfw</li></ul>the model is compatible also with my <a target="_blank" rel="ugc" href="https://civarchive.com/models/310964?modelVersionId=939115">furry enhancer</a> to some point tested with 0.7 strengthMade by <a target="_blank" rel="ugc" href="https://civarchive.com/user/freek22">Freek22</a><h3 id="please-check-out-my-other-models-too-and-give-like-to-support-my-work-)">Please check out my other models too and give like to support my work ;-)</h3>

Ratatoskr (Animal, Creature and Furry) [Flux Kontext]

This is the first trained Version that is using like i mentioned the V1 Block merged versionIts trained now at 175 paired images i created on the Ratatoskr Database. Because of the difference of captaining of kontext to my standard model database i did write all the caption by hand that alone took over 9 hours the training time itself did took some days...<ul><li>the training helped a lot to "repair the damage" of the block merge with the standard flux kontext model</li><li>way more consistent</li><li>better in sfw and nsfw</li></ul>Note: for best quality use the Fp16 or gguf variant the FP8 is only for lower Hardware SettingsIf you like to support me please give a like!

ratatoskrAnimalCreatureAnd_v20FP16FP8.safetensors

v2.0 (FP16 & FP8)

v2.0 (GGUF)

v1.0

In Norse mythology, Ratatoskr (Old Norse, generally considered to mean "drill-tooth" or "bore-tooth") is a squirrel who runs up and down the world tree Yggdrasil to carry messages between the eagle perched atop Yggdrasil and to the roots of the tree to Nidhogg.This model is for Animals / Creatures and Furries but can do way more :<h3 id="because-it's-an-flux-kontext-model-its-main-useis-image-to-image-keep-that-in-mind.">Because it's an Flux Kontext model its main use is image to image keep that in mind.</h3>This model can do:<ul><li>Photorealistic</li><li>Digital Art</li><li>Anime</li><li>Comic</li><li>Vector Graphics</li><li>Line art</li><li>Stickers</li><li>can write short text</li><li>furry</li><li>etc</li></ul>This is the Flux Kontext variant of <a target="_blank" rel="ugc" href="https://civitai.com/models/681795/ratatoskr-animal-creature-and-furry-flux">Ratatoskr Flux </a>The use case is for example for editing any picture made with the ratatoskr model series you can find in my profile but its working with any given pictures too.<h3 id="changelog:">Changelog:</h3>V1: First Release Versionthis is a block merged model made with the Original Kontext Model, and Parts of <a target="_blank" rel="ugc" href="https://civitai.com/models/681795/ratatoskr-animal-creature-and-furry-flux">Ratatoskr Flux</a> and <a target="_blank" rel="ugc" href="https://civitai.com/models/1636436/sleipnir-flux">Sleipnir Flux</a>Note: this is "Just" V1 and not directly trained on the Ratatoskr Dataset yet but i will use this block merge for the starting point for an actual finetune (V2) so there will for sure some Updates in the future.V2:This is the first trained Version that is using like i mentioned the V1 Block merged versionIts trained now at 175 paired images i created on the Ratatoskr Database. Because of the difference of captaining of kontext to my standard model database i did write all the caption by hand that alone took over 9 hours the training time itself did took some days...<ul><li>the training helped a lot to "repair the damage" of the block merge with the standard flux kontext model</li><li>way more consistent</li><li>better in sfw and nsfw</li></ul>the model is compatible also with my <a target="_blank" rel="ugc" href="https://civitai.com/models/310964?modelVersionId=939115">furry enhancer</a> to some point tested with 0.7 strengthMade by <a target="_blank" rel="ugc" href="https://civitai.com/user/freek22">Freek22</a><h3 id="please-check-out-my-other-models-too-and-give-like-to-support-my-work-)">Please check out my other models too and give like to support my work ;-)</h3>

This is the first trained Version that is using like i mentioned the V1 Block merged version

Its trained now at 175 paired images i created on the Ratatoskr Database. Because of the difference of captaining of kontext to my standard model database i did write all the caption by hand that alone took over 9 hours the training time itself did took some days...

the training helped a lot to "repair the damage" of the block merge with the standard flux kontext model

way more consistent

better in sfw and nsfw

Note: for best quality use the Fp16 or gguf variant the FP8 is only for lower Hardware Settings

If you like to support me please give a like! you can download the model on civit.

Files with SHA256: 0f39dcb4d4d24e6b4c466d3039036e3a414cbf6c29c4ed19b8775dc890908fc2