This Lora is made to enhance to ability / quality to create anthro and furry, and creatures with all kinds of models. you can also use it to enhance also animals or fur clothing, etc.its trained and tested on my models but it work on also on other types of models include some pony models . i highly recommend to use it with the following models.: <a target="_blank" rel="ugc" href="https://civarchive.com/models/470287/midgard-pony-thl-sdxl">Midgard Pony, </a><a target="_blank" rel="ugc" href="https://civarchive.com/models/192854/ratatoskr-animal-creature-and-furry">Ratatoskr</a> , <a target="_blank" rel="ugc" href="https://tensor.art/models/690973686016215499">Bifröst Project</a> ,<a target="_blank" rel="ugc" href="https://civarchive.com/models/122793/fenrisxl"> Fenrisxl</a> ,<a target="_blank" rel="ugc" href="https://tensor.art/models/695459826601380688">Yggdrasil,</a> <a target="_blank" rel="ugc" href="https://civarchive.com/models/463847/midgard-thl-hybrid">Midgard</a>the lora can be used for SFW and NSFW.Changelog:V1 This is the first Version and still in WIPi recommend using a strength of 0.7-0.9to get realistic output use the trigger word "anthro"for more digital art style "furry"V2.84added around 200+ more training images (around 800 total) and did a complete retain<ul><li>more detailed</li><li>more specim</li><li>better nsfw part (man) wip</li><li>"emotions" ( wip)</li></ul>I recommend using the Model Ratatoskr or Bifröst ProjectPlease be so kind and keep the Showcase clean of heavy NSFW Stuff and check out my other stuff too ;-)and thanks to <a target="_blank" rel="ugc" href="https://civarchive.com/user/S1LV3RC01N">S1LV3RC01N</a> for the help please check out her models tooV5.2this version is completely new trained from ground up, over weeks. on the base of my Bifröst Project Model<ul><li>better look</li><li>more supported models</li><li>more specimen</li><li>better in nsfw</li><li>etci will provide the complete wordlist in the future</li><li>can turn with a higher strength ( 1-1,3 ) basically any model into a furry model 👍😉</li></ul>V6.1Model got retained again with over 342K Steps and a Training time of 300+ Hours<ul><li>More versatile</li><li>better details</li><li>better in NSFW</li><li>compatible with different types of model ( sdxl 1.0, lightning, hayper, turbo, pony)the tagglist is inside the "training" folder i also included some example Pictures with comfy workflow embedded.</li></ul>V1.0 Flux (Photoreal)First Flux Version of the enhancer trained on parts of the SDXL Version of the enhancer but the tagging got optimized for flux. Its able to bring furries in nearly any Flux model.note: it's "only" trained at 960 pictures yet.Note: There will be 2 Versions: Photoreal, and Digital Artthe Digital Art is still in training and follow later.it can do sfw and nsfw.Have fun with this version of the Furry enhancerI can recommend my <a target="_blank" rel="ugc" href="https://civarchive.com/models/684964/workflow-for-ratatoskr-flux-include-custom-clipl">Workflow</a> for it.Also please Check out my Flux Model <a target="_blank" rel="ugc" href="https://civarchive.com/models/681795?modelVersionId=763114">Ratatoskr Flux</a>V3.420 [Flux] (Photoreal)<ul><li>More detailed</li><li>several improvements</li><li>Trained on a way bigger 1.5K pictures database also changed also the tagging a bit too.</li><li>Note: the needed weight of the lora vary a lot between different models the base model is around 0.7 other like my <a target="_blank" rel="ugc" href="https://civarchive.com/models/830270/bifrost-project-flux">Bifröst Project Flux</a> more 0.3-0-4 for example</li></ul>Flux NSFW Mode V1Some people had complained about the NSFW part of the flux Lora this is my answer to that 😁😉This Version is made for enhancing Flux models in the NSFW Area but can also used in lower weight for enhancing overallits trained on my <a target="_blank" rel="ugc" href="https://civarchive.com/models/974353/newdawn-flux">Newdawn Flux Model</a> .<ul><li>Made for Enhancing Comic and Realistic output</li><li>NSFW in general ;-) Enhancing NSFW Details</li><li>adding BJ % Sex</li><li>but in lower amount works as an regular enhancer too (max 0.6)I recommend using the enhancer between 0.7 and 0.9 for Newdawn FluxWorks also with other models but keep in mind it was trained specific on this model so no one knows exactly how good it runs with other models ;-)</li></ul>RealisticV1.3 (SDXL HEL)This Version is trained and tested on my Model <a target="_blank" rel="ugc" href="https://civarchive.com/models/192854/ratatoskr-animal-creature-and-furry">Ratatoskr V10.94 Helheim</a>its trained on the Furry Enhancer Flux Photorealistic databasenote that this model is its a bit its own type of sdxl model that means its not working well with the sdxl base model or other sdxl types.So if you use that stay with the Furry Enhancer 6.1i have tested it with other models too it works also partly on pony models for example with my <a target="_blank" rel="ugc" href="https://civarchive.com/models/470287?modelVersionId=594847">Midgard - Pony</a> but also Hayden's <a target="_blank" rel="ugc" href="https://civarchive.com/models/125492?modelVersionId=1189343">YiffMix Realism</a> did work so its likely that it works with other Pony and furry model too but no guarantee for thatWeights: For the Ratatoskr V10.94 Helheim I can recommend a weight between 0.3 and 0.8 Note: with a higher weight the model will lose creativity<h3 id="flux-krea-v2.3">Flux Krea V2.3</h3>This Enhancer Version is trained on the Flux Krea ModelHow the model works and technical data details visit <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev">https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev (FP8)</a>This lora is recommended for realistic output on animals, anthro, furry and creature'sThe model is tested with the <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev">FLUX.1-Krea-dev</a>and my <a target="_blank" rel="ugc" href="https://civarchive.com/models/681795/ratatoskr-animal-creature-and-furry-flux-dev-krea?modelVersionId=2119045">Ratatoskr Krea V11.39</a> Model for settings:For the FLUX.1-Krea-dev i had my best results with 0.85 strengthbecause part of it are already in my <a target="_blank" rel="ugc" href="https://civarchive.com/models/681795/ratatoskr-animal-creature-and-furry-flux-dev-krea?modelVersionId=2119045">Ratatoskr Krea V11.39 </a>the settings are between 0.2 and 0.7This version is for <a target="_blank" rel="ugc" href="https://huggingface.co/Qwen/Qwen-Image">Qwen Image</a>its trained on the furry enhancer database at 118700 stepswhats is better than with flux?<ul><li>more coherent</li><li>better understanding overall</li><li>trained in natural language and e631</li><li>knows many specim</li><li>realistic but can also do drawings</li><li>made for sdw and nsfw</li></ul><h3 id="furry-enhancer-qwen-image-v1.3">Furry Enhancer Qwen Image V1.3</h3>For settings:I choose a strength at 0.85 of the lora can recommend between 0.5 and 0.9i used the following setting:30 stepsEuler / Beta57CFG 3.5For Workflow:you can download the picture and but in comfy or download the workflow found in the training files. or use the all in one workflow <a target="_blank" rel="ugc" href="https://civarchive.com/models/1986585?modelVersionId=2248776">https://civarchive.com/models/1986585?modelVersionId=2248776</a>Please give a like to support my work.it's really not easy to make such lora also the costs are very high!made by freek22This disclaimer is not here without reasons. please have in mind this is like a virtual showroom and posting extreme stuff is like 💩 on my desk in real live 😉made by <a target="_blank" rel="ugc" href="https://civarchive.com/user/freek22/models">Freek22</a><h3 id="please-give-a-like-to-support-my-work">please give a like to support my work</h3>

Furry Enhancer

Like the other Furry Enhancer this lora is trained to add details and do an more overall realistic output.this lora version is trained on on the model <a target="_blank" rel="ugc" href="https://civitai.com/models/1022641?modelVersionId=1523727">Helheim Flux</a> with on my high res database. after that the model got converted to be compatible with the new Open Source model <a target="_blank" rel="ugc" href="https://civitai.com/models/1330309?modelVersionId=1501971">Chroma</a>by Silver thanks again for that. the model needs not really trigger words but anthro is more preferred for realistic outcome and furry more in the digital art area The Model is tested on Chroma and Helheim flux for settings Chroma prefers a lora weight between 0.7 and 0.9Helheim Flux a strength between 0.5 and 0.8If you want support my work please give a like ;-)here are someInfos About Chroma:please give this project a visit . i also plan in the future to train on this model base ;-)Chroma is a 8.9B parameter model based on FLUX.1-schnell (technical report coming soon!). It’s fully Apache 2.0 licensed, ensuring that anyone can use, modify, and build on top of it—no corporate gatekeeping.Custom Node for using Chroma: <a target="_blank" rel="ugc" href="https://github.com/lodestone-rock/ComfyUI_FluxMod">https://github.com/lodestone-rock/ComfyUI_FluxMod</a> Original model weights: <a target="_blank" rel="ugc" href="https://huggingface.co/lodestones/Chroma">https://huggingface.co/lodestones/Chroma</a> Mixed Quantization bf16/fp8(Load with bf16 quant_mode): <a target="_blank" rel="ugc" href="https://huggingface.co/silveroxides/Chroma-fp8-bf16-mixed-quant">https://huggingface.co/silveroxides/Chroma-fp8-bf16-mixed-quant</a> T5 text encoder: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/stable-diffusion-3.5-fp8/tree/main/text_encoders">https://huggingface.co/Comfy-Org/stable-diffusion-3.5-fp8/tree/main/text_encoders</a> Custom Node required to use GGUF models: <a target="_blank" rel="ugc" href="https://github.com/city96/ComfyUI-GGUF">https://github.com/city96/ComfyUI-GGUF</a> Chroma model and T5 encoder as GGUF: <a target="_blank" rel="ugc" href="https://huggingface.co/silveroxides/Chroma-GGUF">https://huggingface.co/silveroxides/Chroma-GGUF</a> <a target="_blank" rel="ugc" href="https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf">https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf</a> Experimental non-official LoRA: <a target="_blank" rel="ugc" href="https://huggingface.co/silveroxides/Chroma-LoRA-Experiments">https://huggingface.co/silveroxides/Chroma-LoRA-Experiments</a> Lightweight fast upscaler: <a target="_blank" rel="ugc" href="https://openmodeldb.info/models/4x-Nomos8k-span-otf-medium">https://openmodeldb.info/models/4x-Nomos8k-span-otf-medium</a>

Files with SHA256: 050240b8cb3dd4ecf0c03d1c1c262f981487acf25081641e21f65386b3ec2638