<h2 id="realcore-pony-v2.0-updates">RealCore Pony v2.0 Updates</h2>🌍 More diverse facial features with reduced Asian bias💡 Significantly improved lighting with elimination of unwanted overexposure🎯 Enhanced prompt adherence and instruction following<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/59a06cc4-84d4-4d6a-8fb5-0f53d093699a/width=525/59a06cc4-84d4-4d6a-8fb5-0f53d093699a.jpeg" /><h2 id="realcore-pony-v1.0">RealCore Pony v1.0</h2>A powerful SDXL merge built on Pony Diffusion V6 XL, blending multiple high-quality realistic models and custom LoRAs to deliver lifelike, emotionally rich, and anatomically accurate generations. Whether you're creating intimate portraits, photos, or detailed NSFW content — RealCore Pony strikes the perfect balance between realism, expressiveness, and stylistic flexibility.<pre><code>📌 Note: All example images and videos were generated using the DMD2 LoRA with the LCM sampler (4–8 steps) in ComfyUI, demonstrating the model’s speed and quality under accelerated inference.</code></pre><h3 id="important-considerations:">⚠️ Important considerations:</h3>While RealPonyCore excels in NSFW realism, it is less diverse in artistic styles and facial variety compared to RealCore XL. It prioritizes anatomical fidelity and photo-like rendering over broad stylistic range.Like most Pony-based realism models, it struggles with low-resolution generations. To address this, RealCore Pony intentionally incorporates high-resolution-trained components and omits low-res-optimized layers.Recommendation: Always use HiRes Fix (or an equivalent upscaling + detail refinement pass) for best results.You can also take a look at the Huggingface model repository, there is an fp32 version there 👉 <a target="_blank" rel="ugc" href="https://huggingface.co/rityak/RealCore_Pony">RealCore Pony on CivitAI</a><h3 id="comfyui-workflows">🧩 ComfyUI Workflows</h3>📥 <a target="_blank" rel="ugc" href="https://huggingface.co/rityak/RealCore_Pony/resolve/main/RealPonyCoreXL.json?download=true">Download LCM DMD2 Workflow</a>⚙️ To use KSamplerWithNAG, install the ComfyUI-NAG custom node:<pre><code>cd ComfyUI/custom_nodes 
git clone https://github.com/xmarre/ComfyUI-NAG.git</code></pre><hr /><h1 id="dlya-russkoyazychnyh-polzovatelej">Для русскоязычных пользователей</h1>Если вы интересуетесь нейросетями, LLM, Stable Diffusion и хотите пообщаться в тёплой компании, присоединяйтесь к нашему ламповому чату: 👉 <a target="_blank" rel="ugc" href="https://t.me/ritya_smokeroom">@ritya_smokeroom</a>

RealCore Pony

🧾 Checkpoint Recipe<pre><code>version 0.1.0
model "ritya\\RealCore_Pony_v10.safetensors" model_config="sdxl-sgm" merge_space="weight"
model "pony\\HanfuPonyNSFW_ponyV3.safetensors" model_config="sdxl-sgm" merge_space="weight"
model "pony\\bigLove_pony3.safetensors" model_config="sdxl-sgm" merge_space="weight"
model "pony\\damnIllustriousPony_v30OUTDATED.safetensors" model_config="sdxl-sgm" merge_space="weight"
merge "🔨_karcher_mean_with_json" &amp;1 &amp;2 &amp;3 json_params="{
 \"global\": \"0.234,0.383,0.383\",
 \"max_iter\": 30,
 \"tol\": 3e-7,
 \"OUT04\": \"0.333,0.226,0.441\",
 \"OUT05\": \"0.204,0.301,0.495\",
 \"OUT06\": \"0.333,0.226,0.441\",
 \"OUT08\": \"0.231,0.385,0.385\"
}"
dict BASE=1.0 IN00=0.0 IN01=0.0 IN02=0.0 IN03=0.0 IN04=0.0 IN05=0.0 IN06=0.0 IN07=0.0 IN08=0.0 M00=0.0 OUT00=0.0 OUT01=0.0 OUT02=0.0 OUT03=0.25 OUT04=0.5 OUT05=0.75 OUT06=0.5 OUT07=0.5 OUT08=0.5 VAE=0.0
literal &amp;5 model_config="sdxl-supermerger_blocks" merge_space="param"
merge "convert_sdxl_blocks_to_sgm" &amp;6
merge "weighted_sum" &amp;0 &amp;4 &amp;7
model "pony\\realistic\\RSGRL-CR-PONY(10_10_25).safetensors" model_config="sdxl-kohya_kohya_lora" merge_space="weight"
merge "convert_'sdxl-kohya_kohya_lora'_to_base" &amp;9
merge "convert_'sdxl-kohya'_to_'sdxl-sgm'" &amp;10
model "pony\\realistic\\lora.TA_trained.safetensors" model_config="sdxl-kohya_kohya_lora" merge_space="weight"
merge "convert_'sdxl-kohya_kohya_lora'_to_base" &amp;12
merge "convert_'sdxl-kohya'_to_'sdxl-sgm'" &amp;13
model "pony\\realistic\\BSS_NEOSTR.safetensors" model_config="sdxl-kohya_kohya_lora" merge_space="weight"
merge "convert_'sdxl-kohya_kohya_lora'_to_base" &amp;15
merge "convert_'sdxl-kohya'_to_'sdxl-sgm'" &amp;16
model "pony\\realistic\\BSS_CNMTK-R(Restored).safetensors" model_config="sdxl-kohya_kohya_lora" merge_space="weight"
merge "convert_'sdxl-kohya_kohya_lora'_to_base" &amp;18
merge "convert_'sdxl-kohya'_to_'sdxl-sgm'" &amp;19
merge "🔨_ties_lora_with_json" &amp;11 &amp;14 &amp;17 &amp;20 json_params="{
 \"lambda\": 1.0,
 \"weights\": \"0.400,0.350,0.200,0.150\",
 \"density\": 0.4,
 \"vote_sgn\": true,
 \"apply_stock\": false,
 \"apply_median\": false
}"
literal 1.0 model_config="sdxl-sgm" merge_space="param"
merge "pick_component" &amp;22 "clip_l"
merge "pick_component" &amp;22 "clip_g"
merge "fallback" &amp;23 &amp;24
literal 0.0 model_config="sdxl-sgm" merge_space="param"
merge "pick_component" &amp;26 "vae"
merge "fallback" &amp;25 &amp;27
merge "pick_component" &amp;22 "diffuser"
merge "fallback" &amp;28 &amp;29
merge "add_difference" &amp;8 &amp;21 &amp;30
merge "fallback" &amp;31 &amp;8
merge "add_cosine_a" &amp;0 &amp;32 0.5
merge "pick_component" &amp;26 "diffuser"
merge "fallback" &amp;28 &amp;34
merge "weighted_sum" &amp;33 &amp;4 &amp;35</code></pre>

Files with SHA256: 9147c8c1bb14d13cce45c833adc9e29305ee12a131139b61ef4b9cf389c6bcd1