<h2 id="justanotherfurrymerge">JustAnotherFurryMerge</h2>JustAnotherFurryMerge (JAFM) is my personal merge I made using ComfyUI. It first started as experiment with merging random furry models I have. Turns out it gens very well so I decided to share it with anybody out here. It is intended to generate furry anthros. It can do males and possibly anime as well, however I'm not into that. Using mostly e6 tags for my gens.This merge is eps prediction. It has a piece of v-pred in it, but since basemodel is eps the output model is eps as well.<h3 id="recommended-settings:">Recommended settings:</h3>Steps: 10 - 30 (16+ for zoom-in better quality) CFG: 2 - 6 (6+ if you like oversaturation) Sampler: Euler a, dpm++ 2m sde, ddpm, seeds 2 Scheduler: beta &gt; karras &gt; normal Other uncommon works also, just keep experimentingPrompting: Using quality tags seems to improve quality in some way. Probably does not matter if you put them on beggining or end of prompt. Use whatever you prefer. Resolutions: Anything between 0.9 and 2.4 MPx is okay. Unless too vide or tall.<h3 id="running-showcase-workflows:">Running showcase workflows:</h3>First make sure you have latest version of ComfyUI with Manager with and all custom nodes installed. Copy pasting again from Civitai should not throw any missing nodes. Don't forget to check suggested resources for detectors I used. They need to be placed in "models/ultralytics/segm/" on the same drive your ComfyUI is saved. Having "ultralytics: models/ultralytics/" in "extra_model_paths.yaml" file does not work and probably never will.If workflows from older versions doesn't run with correct model/vae selected, try using from never ones, copy prompt, seed and choose model. This might happen as ComfyUI with customnodes getting frequent updates. I also genned v2.0 showcases on high resolutions. Anyway I changed workflow on some showcases in v3.0, next might be different again.<h3 id="version-history:">Version history:</h3><ul><li>1.0 &amp; 1.0unstyled - First release</li><li>2.0 &amp; 2.0unstyled - Hires rawgens quality improvement</li><li>3.0 &amp; 3.0unstyled - Small knowledge enchancement</li></ul><h3 id="credits">Credits</h3>Thank you all for creating such nice models! Without you, my own would not be possible:Checkpoints Agri_Yob, AI_nstein, Anomalous_Anonymous, Crody, EJtech, jhonny09, kftiger, LatteLeopard, Ocean3, Old_Arctenox, ONOMAAI, RodAndRog, SXCD2719Loras Anzatiridonia, EauDeNoire, iamddtla, Meower2024, ntc, UnholyDesiresStudio, Volnovik, w4r10ckVae First 2 releases stabilityai, ongoing myselfPost your gens, share if you like it! And don't forget, no reprints please.

JustAnotherFurryMerge

Third version - Small knowledge enhancement (7 models + 7 loras) + my own <a target="_blank" rel="ugc" href="https://civitai.com/models/2248393?modelVersionId=2531106">Better Colors Vae Monumental</a>Base = <a target="_blank" rel="ugc" href="https://civitai.com/models/1759720?modelVersionId=2302557">v2.0</a> * 0.6 + <a target="_blank" rel="ugc" href="https://civitai.com/models/1530301?modelVersionId=2190389">Arctenox's Personal v0.5C</a> * 0.06 + <a target="_blank" rel="ugc" href="https://civitai.com/models/503815?modelVersionId=2484701">NovaFurry IL v14.0</a> * 0.08 + <a target="_blank" rel="ugc" href="https://civitai.com/models/1812608?modelVersionId=2162562">YobboIllustrious v2</a> * 0.06 + <a target="_blank" rel="ugc" href="https://civitai.com/models/1893897?modelVersionId=2482266">Augenstein v5B</a> * 0.06 + <a target="_blank" rel="ugc" href="https://civitai.com/models/1999219?modelVersionId=2262886">Ultra4illustrious v1.0</a> * 0.07 + <a target="_blank" rel="ugc" href="https://civitai.com/models/2078828?modelVersionId=2352201">Cinema l'usine Lumière</a> * 0.07JAFM v3.0 = Base + <a target="_blank" rel="ugc" href="https://civitai.com/models/1191424?modelVersionId=1990837">PornMaster - rule 34 prompts v2</a> * 0.1 + <a target="_blank" rel="ugc" href="https://civitai.com/models/1377820?modelVersionId=1963644">Add Micro Details v5.0 IL</a> * 0.05 + <a target="_blank" rel="ugc" href="https://civitai.com/models/1377820?modelVersionId=2409201">Add Micro Details v3.0 NAI</a> * 0.05 + <a target="_blank" rel="ugc" href="https://civitai.com/models/987736?modelVersionId=1147221">NoobAI-XL Detailer EPS1.1 v1.0</a> * 0.6 + <a target="_blank" rel="ugc" href="https://civitai.com/models/122359?modelVersionId=135867">Detail Tweaker XL v1.0</a> * 0.5 + <a target="_blank" rel="ugc" href="https://civitai.com/models/670378?modelVersionId=750428">Eyes High Definition v1</a> * 0.5 + <a target="_blank" rel="ugc" href="https://civitai.com/models/200255?modelVersionId=997426">Hands XL v5.5</a> * 0.75Rule 34 &amp; Hands loras permission to merge granted - Big thanks!

justanotherfurrymerg_v30.safetensors

v3.0

v3.0unstyled

v2.0unstyled

v2.0

v1.0unstyled

v1.0

creator: AndHorJustAnotherFurryMerge is my personal merge I made using ComfyUI. It first started as experiment with merging random furry models I have. Turns out it gens very well so I decided to share it with anybody out here. It is intended to generate furry anthros. It can do males and possibly anime as well, however I'm not into that. Using mostly e6 tags for my gens.This model is eps prediction. It has a piece of v-pred in it, but since basemodel is eps the output model is eps as well.Recommended settings:Steps: 10 - 30 (16+ for zoom-in better quality) CFG: 2 - 4 (some prompts up to 6) Sampler: Euler a, dpm++ 2m, ddpm, seeds 2 Scheduler: beta &gt; karras &gt; normalPrompting: Using quality tags seems to improve quality in some way. Probably does not matter if you put them on beggining or end of prompt. Do as you wish.Running showcase workflows:Make sure you have latest version of ComfyUI with Manager with all custom nodes installed. Copy pasting from Civitai should not throw any missing nodes. Don't forget to check suggested resources for detectors I used. They need to be placed in "models/ultralytics/segm/" on the same drive your ComfyUI is saved. As of july 2025, having "ultralytics: models/ultralytics/" in "extra_model_paths.yaml" file does not work for some strange reason.Version history:<ul><li>1.0 &amp; 1.0unstyled - first release</li></ul>

Files with SHA256: b95f9e015e2cb2b93e3c158eebf3912bc8e39476f2fbc852566c0b912c6977df