Name: Babes By Stable Yogi (Pony)
Rating: 5 (9065 reviews)
Author: Stable_Yogi

physical violence

revealing clothes

weapon violence

pg-13

corpses

wide hips

convenient censoring

oral invitation

thick thighs

huge breasts

downblouse

suggestive

sexy

pg13

sexual situations

disturbing

male nudity

female swimwear or underwear

male swimwear or underwear

partial nudity

graphic violence or gore

emaciated bodies

exposed female nipple

female nudity

undressed

male underwear

female swimwear

female underwear

breasts out

strapless leotard

breast out

one breast out

gigantic breasts

huge butt

covered nipples

hair over breasts

no panties

sitting on face

nude

lingerie

nsfw

adult toys

nudity

graphic male nudity

illustrated explicit nudity

graphic female nudity

sexual intent

genitals

porn

futanari

hentai

peeing

blowjob

sexual activity

vore

anal

dildo riding

oral

incest

hanging

hate symbols

nazi party

white supremacy

self injury

extremist

hate speech

diapers

urine

scat

child on child

bukkake

fellatio

bikini

cumshot

implied fellatio

eat_cum

cumdrip

cum in pussy

cum on face

after fellatio

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

Pro version of Babes_By_Stable_Yogi Pony is availble on <a target="_blank" rel="ugc" href="https://brandulate.com/">my Patreon</a>Onsite generations are available on this version: <a target="_blank" rel="ugc" href="https://civitai.com/models/166609?modelVersionId=992946￼👉">👉</a> Babes_By_Stable_Yogi: <a target="_blank" rel="ugc" href="https://civitai.com/models/174687?modelVersionId=1779463">https://civitai.com/models/174687?modelVersionId=1779463</a>If there’s another model you’d like to generate images with, just place a bid here and I’ll make it available for onsite generation: <a target="_blank" rel="ugc" href="https://civitai.com/auctions/featured-checkpoints">https://civitai.com/auctions/featured-checkpoints</a>Join me on <a target="_blank" rel="ugc" href="https://brandulate.com/">my Patreon</a>. for exclusive perks and early access to unique resources.To discuss custom LoRa's or models, feel free to connect on <a target="_blank" rel="ugc" href="https://discord.gg/FAgfAeMqys">Discord.</a><ul><li>👍 Like this model to keep me motivated and inspired to create more!</li><li>💬 Drop a comment and let me know what you'd love to see next.</li><li>🌟 Review this model to help me improve and make even better creations.</li><li>🔔 Hit that notification bell to stay updated with my latest models and updates!</li></ul><h3 id="important-usage-tips">Important Usage Tips</h3><ul><li>Add <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=775151">Stable_Yogis_PDXL_Positives</a> at the beginning of your prompt section.</li><li>Add <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=772342">Stable_Yogis_PDXL_Negatives-neg</a> at the beginning of your negative prompt section.</li></ul>

V6 — Natural Portrait Realism V6 is tuned for lifelike, editorial-style portraits that hold up in close-ups and groups. It renders clean skin, true-to-life lighting, and believable fabric/hair detail while staying responsive to prompts (poses, outfits, moods). Works for SFW lifestyle and tasteful NSFW sets.What it does well (based on your images)<ul><li>Group &amp; duo portraits without face collapse; consistent identities across the frame.</li><li>Close-up realism: pores, lashes, subtle freckles; crisp yet natural eyes.</li><li>Texture fidelity: mesh/knit fabrics, belts/buckles, camouflage patterns, braided &amp; curly hair.</li><li>Lighting control: soft indoor, daylight/beach, window light; balanced contrast and shadow roll-off.</li><li>Prompt adherence: outfits/props/locations follow instructions without drifting.</li></ul>Quick Start (SDXL)<ul><li>Sampler: DPM++ SDE Karras / DPM++ 2M SDE Karras (Euler a/DPM2a also good)</li><li>Steps: 22–30 </li><li>CFG: 4–6 </li><li>Resolution: 832×1216, 1024×1024, 1024×1360, 1216×832 (native SDXL sizes)</li><li>Embeddings:<ul><li>Negative: <code>Stable_Yogis_PDXL_Negatives-neg</code></li><li>Positive: <code>Stable_Yogis_PDXL_Positives</code></li></ul></li></ul>Join me on <a target="_blank" rel="ugc" href="https://brandulate.com/">my Patreon</a> for exclusive Pro versions and unique resources.

v6.0_FP16

V6 — Natural Portrait RealismV6 is tuned for lifelike, editorial-style portraits that hold up in close-ups and groups. It renders clean skin, true-to-life lighting, and believable fabric/hair detail while staying responsive to prompts (poses, outfits, moods). Works for SFW lifestyle and tasteful NSFW sets.What it does well (based on your images)<ul><li>Group &amp; duo portraits without face collapse; consistent identities across the frame.</li><li>Close-up realism: pores, lashes, subtle freckles; crisp yet natural eyes.</li><li>Texture fidelity: mesh/knit fabrics, belts/buckles, camouflage patterns, braided &amp; curly hair.</li><li>Lighting control: soft indoor, daylight/beach, window light; balanced contrast and shadow roll-off.</li><li>Prompt adherence: outfits/props/locations follow instructions without drifting.</li></ul>Quick Start (SDXL)<ul><li>Sampler: DPM++ SDE Karras / DPM++ 2M SDE Karras (Euler a/DPM2a also good)</li><li>Steps: 22–30</li><li>CFG: 4–6</li><li>Resolution: 832×1216, 1024×1024, 1024×1360, 1216×832 (native SDXL sizes)</li><li>Embeddings:<ul><li>Negative: <code>Stable_Yogis_PDXL_Negatives-neg</code></li><li>Positive: <code>Stable_Yogis_PDXL_Positives</code></li></ul></li></ul>Join me on <a target="_blank" rel="ugc" href="https://brandulate.com/">my Patreon</a> for exclusive Pro versions and unique resources.

v6.0_BF16

V6 — Natural Portrait RealismV6 is tuned for lifelike, editorial-style portraits that hold up in close-ups and groups. It renders clean skin, true-to-life lighting, and believable fabric/hair detail while staying responsive to prompts (poses, outfits, moods). Works for SFW lifestyle and tasteful NSFW sets.What it does well (based on your images)<ul><li>Group &amp; duo portraits without face collapse; consistent identities across the frame.</li><li>Close-up realism: pores, lashes, subtle freckles; crisp yet natural eyes.</li><li>Texture fidelity: mesh/knit fabrics, belts/buckles, camouflage patterns, braided &amp; curly hair.</li><li>Lighting control: soft indoor, daylight/beach, window light; balanced contrast and shadow roll-off.</li><li>Prompt adherence: outfits/props/locations follow instructions without drifting.</li></ul>Quick Start (SDXL)<ul><li>Sampler: LCM (Euler a also good)</li><li>Steps: 6-10</li><li>CFG: 1.1-2.1</li><li>Resolution: 832×1216, 1024×1024, 1024×1360, 1216×832 (native SDXL sizes)</li><li>Embeddings:<ul><li>Negative: <code>Stable_Yogis_PDXL_Negatives-neg</code></li><li>Positive: <code>Stable_Yogis_PDXL_Positives</code></li></ul></li></ul>Join me on <a target="_blank" rel="ugc" href="https://brandulate.com/">my Patreon</a> for exclusive Pro versions and unique resources.

v6.0_DMD2

<ul><li>This ALT model is a DMD2 fine tuned version.</li></ul>Changes :<ul><li>Increased the CFG acceptance upto 7</li><li>Added support for more samplers like DPM SDE. DPM 2M, DPM 2M SDE</li><li>For using Higher CFG you must increase the steps too.</li><li>For increase in each 1+ CFG increase steps by 2</li><li>Base CFG1.1 and Base Steps 6, Optimal steps 10</li></ul>Recommended Samplers<ul><li>DPM++ SDE</li><li>DPM++ 2M,</li><li>DPM++ 2M SDE</li><li>LCM</li><li>EULER A</li></ul>Optimal Settings<ul><li>Steps: 10</li><li>CFG Scale: 1.1 to 7 (Minimum keep 1.1 makes sure that your negative prompts work)</li><li>Clip Skip: 2</li><li>Resolution: Any SDXL size; for Insta‑ready posts use 896 × 1120 px</li><li>High‑Res Fix: 1.206× upscale with the 4× ClearRealityV1 upscaler (9 steps, denoise 0.1)</li></ul>

v6.0_DMD2_ALT

This version introduces enhanced detail and depth, with training focused on:<ul><li>Natural environments and background variety</li><li>Improved lighting and shadow control</li><li>More accurate anatomy, including hands and body structure</li><li>Balanced NSFW and SFW generation capabilities</li><li>Stronger prompt adherence for precise results</li></ul>⚙️ Recommended Settings<ul><li>Steps: 20+</li><li>Samplers: Euler a, DPM2a, DPM++ SDE Karras, DPM++ 2M SDE Karras</li><li>CFG Scale: 4+</li><li>Resolution: Fully SDXL-compatible sizes</li></ul>Negative Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=772342">Stable_Yogis_PDXL_Negatives-neg</a>Positive Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=775151">Stable_Yogis_PDXL_Positives</a>I am happy to listen to your feedback, Share your thoughts, comments and relevant questions.Join me on <a target="_blank" rel="ugc" href="https://brandulate.com/">my Patreon</a> for exclusive perks and early access to unique resources.To discuss custom Lora's or models, feel free to connect on <a target="_blank" rel="ugc" href="https://discord.gg/shd97NSeTw">Discord</a>.

v5.0

This is a Pony XL based on the DMD2 LoRA, designed for high-detail generations with improved accuracy and prompt control in just 4 to6 steps.Training in this version focused on:<ul><li>Natural environments and diverse background styles</li><li>Enhanced lighting and shadow dynamics</li><li>Improved anatomical structure, especially hands and body forms</li><li>Balanced handling of both NSFW and SFW outputs</li><li>Stronger prompt adherence for more reliable results</li></ul>⚙️ Recommended Settings<ul><li>CFG Scale: 1 or 1.5</li><li>Steps: 6+ (8 for good quality, 10 for best results)</li><li>Samplers: Euler a, LCM</li><li>Resolution: Works with most Pony / SDXL resolutions</li></ul>Negative Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=772342">Stable_Yogis_PDXL_Negatives-neg</a>Positive Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=775151">Stable_Yogis_PDXL_Positives</a>I am happy to listen to your feedback, Share your thoughts, comments and relevant questions.Join me on <a target="_blank" rel="ugc" href="https://brandulate.com/">my Patreon</a> for exclusive perks and early access to unique resources.To discuss custom Lora's or models, feel free to connect on <a target="_blank" rel="ugc" href="https://discord.gg/shd97NSeTw">Discord</a>.

v5.0_4s

Adjustments to this versionOverall cleaner and sharper image qualitySlightly more intricate detailing throughout the imageEnhanced accuracy in rendering hands and feetImproved control over lighting and darknessBetter alignment with given promptsMore nuanced and refined color representationNoticeable enhancements to skin textureSlightly improved facial structures from multiple anglesFixed the bug that caused same face in all images.Steps: 20+Sampler: Euler a, DPm2a, DPM++ SDE Karras, DPM++ 2M SDE KarrasCFG scale: 4+Size: All SDXL Compatible SizesNegative Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=772342">Stable_Yogis_PDXL_Negatives-neg</a>Positive Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=775151">Stable_Yogis_PDXL_Positives</a>I am happy to listen to your feedback, Share your thoughts, comments and relevant questions.Join me on <a target="_blank" rel="ugc" href="https://brandulate.com/">my Patreon</a> for exclusive perks and early access to unique resources.To discuss custom Lora's or models, feel free to connect on <a target="_blank" rel="ugc" href="https://discord.gg/shd97NSeTw">Discord</a>.

PONY_V4

Works best with Euler A and DPM++ SDE you can try others samplers too.CFG 4 to 7Steps 20 and aboveResolutions:<ul><li>1280x768</li><li>1280x720</li><li>832x1216</li><li>768x1024</li><li>640x1024</li><li>512x768</li></ul>ADetailer RequiredHighers Fix OptionalFace Restore OptionalUpscaler = 4x-UltraSharpSteps = 4+Denoise = 0.2 to 0.3Upscale by = 1.25 and AboveNegative Prompts(Download this negative embedding for best results) <a target="_blank" rel="ugc" href="https://civitai.com/models/177792/negative-embeddingsbystableyogi">Stable_Yogis_PDXL_Negatives</a>(Score tags like =&gt;score_4, score_5_up, score_4_up, not required with this embedding )Positive Prompts(Download this positive embedding for best results) <a target="_blank" rel="ugc" href="https://civitai.com/models/177792/negative-embeddingsbystableyogi">Stable_Yogis_PDXL_Positives</a>(Score tags like =&gt;score_9, score_8_up, score_7_up, not required with this embedding )Join me on <a target="_blank" rel="ugc" href="https://brandulate.com/">my Patreon</a> for exclusive perks and early access to unique resources.To discuss custom Lora's or models, feel free to connect on <a target="_blank" rel="ugc" href="https://discord.gg/shd97NSeTw">Discord</a>.

PONY_V3

Works best with DPM++ SDE , Euler A, you can try others samplers too.CFG 4.5 and aboveSteps 20 and aboveResolutions:<ul><li>1280x768</li><li>1280x720</li><li>832x1216</li><li>768x1024</li><li>640x1024</li><li>512x768</li></ul>ADetailer RequiredHighers Fix RequiredThis version Requires SDXL VAE ( <a target="_blank" rel="ugc" href="https://civitai.com/models/296576/sdxl-vae">Download link</a> )Upscaler = 4x-UltraSharpSteps = 5+Denoise = 0.2 to 0.35Upscale by = 1.5 and AboveNegative Prompts (Download this negative embedding for best results) <a target="_blank" rel="ugc" href="https://civitai.com/models/177792/negative-embeddingsbystableyogi">Stable_Yogis_PDXL_Negatives</a>(Score tags like =&gt;score_4, score_5_up, score_4_up, not required with this embedding )Positive Prompts (Download this positive embedding for best results) <a target="_blank" rel="ugc" href="https://civitai.com/models/177792/negative-embeddingsbystableyogi">Stable_Yogis_PDXL_Positives</a>(Score tags like =&gt;score_9, score_8_up, score_7_up, not required with this embedding )=========================================================

PONY_V2

Steps: 20+Sampler: Euler aCFG scale: 4+Size: All SDXL Compatible SizesNegative Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=772342">Stable_Yogis_PDXL_Negatives-neg</a>Positive Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=775151">Stable_Yogis_PDXL_Positives</a>Join me on <a target="_blank" rel="ugc" href="https://brandulate.com/">my Patreon</a> for exclusive perks and early access to unique resources.To discuss custom Lora's or models, feel free to connect on <a target="_blank" rel="ugc" href="https://discord.gg/shd97NSeTw">Discord</a>.

XL_V4

This version is is Better with anatomy and NSFW. Steps: 20+, Sampler: Euler a, CFG scale: 4+, Face restoration: CodeFormer, Size: 720x1260, And all SDXL Compatible Sizes.Clip skip: 2, ADetailer model: RequiredNegative prompt: <a rel="ugc" href="https://civitai.com/models/177792?modelVersionId=772342">Stable_Yogis_PDXL_Negatives-neg</a>

XL_V3

Babes_XL_V2_By_Stable_Yogi ❤Discover our versatile new model—the perfect all-rounder for all your image needs! With enhanced body anatomy, hands, colors, and detailed tweaks, it delivers outstanding results every time. Give it a try and you’ll love it!Works best with DPM++ SDE is best, you can try others samplers too.CFG 4.5 and aboveSteps 20 and aboveResolutions:<ul><li>1280x768</li><li>1280x720</li><li>832x1216</li><li>768x1024</li><li>640x1024</li><li>512x768</li></ul>ADetailer RequiredHighers Fix RequiredThis version Requires SDXL VAE ( <a target="_blank" rel="ugc" href="https://civitai.com/models/296576/sdxl-vae">Download link</a> )Upscaler = 4x-UltraSharpSteps = 5+Denoise = 0.2 to 0.3Upscale by = 1.5 and AboveNegative Prompts(Download this negative embedding for best results) <a target="_blank" rel="ugc" href="https://civitai.com/models/177792/negative-embeddingsbystableyogi">Stable_Yogis_PDXL_Negatives</a>Positive Prompts(Download this positive embedding for best results) <a target="_blank" rel="ugc" href="https://civitai.com/models/177792/negative-embeddingsbystableyogi">Stable_Yogis_PDXL_Positives</a>

XL_V2

PONY_V4_FP32_Fix

This is a Pony Checkpoint , based on DMD2 LoraCFG 1, 1.5 Works with most Pony/SDXL ResolutionsSteps: 6+ (8 for good and 10 for best results)Sampler: Euler a, DPm2a, DPM++ SDE Karras, DPM++ 2M SDE KarrasCFG scale: 1, 1.5,Size: All SDXL Compatible SizesNegative Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=772342">Stable_Yogis_PDXL_Negatives-neg</a>Positive Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=775151">Stable_Yogis_PDXL_Positives</a>I am happy to listen to your feedback, Share your thoughts, comments and relevant questions.Learn More about it here <a target="_blank" rel="ugc" href="https://huggingface.co/tianweiy/DMD2">https://huggingface.co/tianweiy/DMD2</a>Join me on <a target="_blank" rel="ugc" href="https://brandulate.com/">my Patreon</a> for exclusive perks and early access to unique resources.To discuss custom Lora's or models, feel free to connect on <a target="_blank" rel="ugc" href="https://discord.gg/shd97NSeTw">Discord</a>.

PONY_V4_DMD2_Fix

This is a Pony Checkpoint , based on Hyper LoraCFG 1, 1.5 Works with most Pony/SDXL ResolutionsSteps: 6+ (8 for good and 10 for best results)Sampler: Euler a, DPm2a, DPM++ SDE Karras, DPM++ 2M SDE KarrasCFG scale: 1, 1.5,Size: All SDXL Compatible SizesNegative Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=772342">Stable_Yogis_PDXL_Negatives-neg</a>Positive Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=775151">Stable_Yogis_PDXL_Positives</a>I am happy to listen to your feedback, Share your thoughts, comments and relevant questions.Join me on <a target="_blank" rel="ugc" href="https://brandulate.com/">my Patreon</a> for exclusive perks and early access to unique resources.To discuss custom Lora's or models, feel free to connect on <a target="_blank" rel="ugc" href="https://discord.gg/shd97NSeTw">Discord</a>.

PONY_V4_Hyper_Fix

This is a Pony Checkpoint , based on Lightning LoraCFG 1, 1.5 Works with most Pony/SDXL ResolutionsSteps: 6+ (8 for good and 10 for best results)Sampler: Euler a, DPm2a, DPM++ SDE Karras, DPM++ 2M SDE KarrasCFG scale: 1, 1.5,Size: All SDXL Compatible SizesNegative Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=772342">Stable_Yogis_PDXL_Negatives-neg</a>Positive Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=775151">Stable_Yogis_PDXL_Positives</a>I am happy to listen to your feedback, Share your thoughts, comments and relevant questions.Join me on <a target="_blank" rel="ugc" href="https://brandulate.com/">my Patreon</a> for exclusive perks and early access to unique resources.To discuss custom Lora's or models, feel free to connect on <a target="_blank" rel="ugc" href="https://discord.gg/shd97NSeTw">Discord</a>.

PONY_V4_Lightning_Fix

Steps: 20+Sampler: Euler aCFG scale: 4+Size: All SDXL Compatible SizesNegative Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=772342">Stable_Yogis_PDXL_Negatives-neg</a>Positive Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=775151">Stable_Yogis_PDXL_Positives</a>

V4_XL_FP32

Steps: 6 or 7 steps works goodSampler: Euler aCFG scale: 1, 1.5,Size: All SDXL Compatible SizesNegative Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=772342">Stable_Yogis_PDXL_Negatives-neg</a>Positive Embedding: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=775151">Stable_Yogis_PDXL_Positives</a>

V4_XL_DMD2

V4_XL_Hyper

V4_XL_Lightning

This is a 4 Step Pony Version, based on DMD2(Just like a Lightning or Hyper Checkpoint)CFG 1 Works with most ResolutionsUse Euler a, LCM, or LCM Karras With this model.Highers Fix 1.5 with Ultrasharp4x UpscalerAdetailer as required Learn More about it here <a target="_blank" rel="ugc" href="https://huggingface.co/tianweiy/DMD2">https://huggingface.co/tianweiy/DMD2</a>

PONY_V3_DMD2

Pony_V3_Hyper_4S ❤Works best with EULER ACFG 1Steps 4Resolutions:<ul><li>1280x768</li><li>1280x720</li><li>832x1216</li><li>768x1024</li><li>640x1024</li><li>512x768</li></ul>ADetailer RequiredHighers Fix OptionalUpscaler = 4x-UltraSharpSteps = 5+Denoise = 0.2 to 0.3Upscale by = 1.5 and Above

Pony_V3_Hyper

Pony_V3_lightning_4S ❤Works best with EULER ACFG 1 or 1.5Steps 4 , 6 , 8Resolutions:<ul><li>1280x768</li><li>1280x720</li><li>832x1216</li><li>720x1260</li><li>768x1024</li><li>640x1024</li><li>512x768</li></ul>ADetailer RequiredHighers Fix OptionalUpscaler = 4x-UltraSharpSteps = 5+Denoise = 0.2 to 0.3Upscale by = 1.5 and Above

PONY_V3_Lightning

How to Use the Inpainting ModelRecommended Settings:<ul><li>Inpainting Mode: Soft inpainting</li><li>Sampler: Euler a</li><li>Scheduler Type: Uniform</li><li>Mask Blur: Set between 4 and 8 for optimal edge blending</li><li>CFG Scale: 3 to 6 for control over the prompt’s influence</li><li>Denoising Strength: 0.9 for detailed inpainting results</li></ul>Soft Inpainting Adjustments:<ul><li>Set "Transition Contrast Boost" to 1 (default is 4)</li><li>Adjust "Difference Threshold" to between 0.1 and 0.25 (default is 0.5)</li></ul>Tips for Best Results:<ol><li>Masking Quality: Use the “Only Masked” option for the best quality, ensuring that the model focuses on the masked areas.</li><li>Mask Content: Start with “Masked content: original.” If that doesn’t provide the desired results, try “latent noise” or “fill” to achieve smoother blending.</li><li>Image Size: For best results with SDXL, aim for an image size with a combined width and height between 2000 and 2500 pixels. Alternatively, scale your image around this size range using aspect ratio helpers.</li><li>Creative Masks: Use masking creatively to change poses or settings. For example, if you want to adjust the character’s posture or add specific items, mask the areas where these adjustments should occur.</li><li>Refining Results: For complex edits, use a high-quality refining model (like "realistic refinement") set between 0.8 and 0.9 to sharpen and finalize the output.</li><li>Extended Masking: When inpainting a small section, consider masking additional areas at the top or bottom so the model processes the full image context for consistency.</li><li>Minimal Prompts: Keep your prompts concise. The model responds well with minimal guidance, allowing it to draw from the mask and original image for detail.</li></ol>Example Scenarios<ul><li>Basic Clothing Change:<ul><li>Prompt: “woman, wearing a formal gown”</li><li>Mask the existing clothing area to replace with the new outfit.</li><li>Additional prompt (if needed): "woman, standing in profile with formal gown"</li></ul></li><li>Pose Adjustment:<ul><li>Initial prompt: “woman, lying on her back”</li><li>To change the pose, mask specific parts (such as arms or legs) to create a new pose.</li><li>Example: “woman, sitting with crossed legs”</li></ul></li><li>Context Change for Creative Effect:<ul><li>Initial prompt: “woman, wearing autumn coat, standing in forest”</li><li>Mask the coat to replace it with a winter jacket, or mask the background to add fog or snowfall.</li><li>Example for new prompt: “woman, winter jacket, snowy forest”</li></ul></li></ul>

PONY_V3_Inpaint

BABES_BY_STABLE_YOGI_V7_SD1.5_INPAINT_Fp16How to Use the Inpainting ModelRecommended Settings:<ul><li>Inpainting Mode: Soft inpainting</li><li>Sampler: Euler a</li><li>Scheduler Type: Uniform</li><li>Mask Blur: Set between 4 and 8 for optimal edge blending</li><li>CFG Scale: 3 to 6 for control over the prompt’s influence</li><li>Denoising Strength: 0.9 for detailed inpainting results</li></ul>Soft Inpainting Adjustments:<ul><li>Set "Transition Contrast Boost" to 1 (default is 4)</li><li>Adjust "Difference Threshold" to between 0.1 and 0.25 (default is 0.5)</li></ul>Tips for Best Results:<ol><li>Masking Quality: Use the “Only Masked” option for the best quality, ensuring that the model focuses on the masked areas.</li><li>Mask Content: Start with “Masked content: original.” If that doesn’t provide the desired results, try “latent noise” or “fill” to achieve smoother blending.</li><li>Image Size: For best results with SDXL, aim for an image size with a combined width and height between 2000 and 2500 pixels. Alternatively, scale your image around this size range using aspect ratio helpers. For SD1.5 Aim for 512x768.</li><li>Creative Masks: Use masking creatively to change poses or settings. For example, if you want to adjust the character’s posture or add specific items, mask the areas where these adjustments should occur.</li><li>Refining Results: For complex edits, use a high-quality refining model (like "realistic refinement") set between 0.8 and 0.9 to sharpen and finalize the output.</li><li>Extended Masking: When inpainting a small section, consider masking additional areas at the top or bottom so the model processes the full image context for consistency.</li><li>Minimal Prompts: Keep your prompts concise. The model responds well with minimal guidance, allowing it to draw from the mask and original image for detail.</li></ol>Example Scenarios<ul><li>Basic Clothing Change:<ul><li>Prompt: “woman, wearing a formal gown”</li><li>Mask the existing clothing area to replace with the new outfit.</li><li>Additional prompt (if needed): "woman, standing in profile with formal gown"</li></ul></li><li>Pose Adjustment:<ul><li>Initial prompt: “woman, lying on her back”</li><li>To change the pose, mask specific parts (such as arms or legs) to create a new pose.</li><li>Example: “woman, sitting with crossed legs”</li></ul></li><li>Context Change for Creative Effect:<ul><li>Initial prompt: “woman, wearing autumn coat, standing in forest”</li><li>Mask the coat to replace it with a winter jacket, or mask the background to add fog or snowfall.</li><li>Example for new prompt: “woman, winter jacket, snowy forest”</li></ul></li></ul>

V7_SD1.5_INPAINT

This version is is Better with anatomy and NSFW. based on DMD2 ( Works Similar like lightning and hyper, skin texture is better )This version is Based on DMD2 ( <a target="_blank" rel="ugc" href="https://huggingface.co/tianweiy/DMD2">https://huggingface.co/tianweiy/DMD2</a> )Steps: 4, 5, 6Sampler: Euler a,CFG scale: 1, 1.5Face restoration: CodeFormer,Size: 720x1260, And all SDXL Compatible Sizes.Clip skip: 2,ADetailer model: RequiredNegative prompt: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=772342">Stable_Yogis_PDXL_Negatives-neg</a>

XL_V3_DMD2

This version is is Better with anatomy and NSFW.Steps: 4, 5, 6Sampler: Euler a,CFG scale: 1, 1.5 or 2Face restoration: CodeFormer,Size: 720x1260, And all SDXL Compatible Sizes.Clip skip: 2,ADetailer model: RequiredNegative prompt: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=772342">Stable_Yogis_PDXL_Negatives-neg</a>

XL_V3_HYPER

This version is is Better with anatomy and NSFW.Steps: 4, 5 ,6Sampler: Euler a,CFG scale: 1, 1.5, 2Face restoration: CodeFormer,Size: 720x1260, And all SDXL Compatible Sizes.Clip skip: 2,ADetailer model: RequiredNegative prompt: <a target="_blank" rel="ugc" href="https://civitai.com/models/177792?modelVersionId=772342">Stable_Yogis_PDXL_Negatives-neg</a>

XL_V3_Lightning

BABES_BY_STABLE_YOGI_V7 SD1.5 Fp16Steps: 20+Sampler: DPM++ SDE or Your ChoiceCFG scale: 4+Face restoration: CodeFormer, Size: 512x768, 600x900 and your ChoiceADetailer : RequiredNegative Embeddings: NEG_EMBED_STABLE_YOGI_V3 , Morenegative_Stable_Yogi-neg

V7_SD1.5

This is a 4 Step Pony Version, based on DMD2(Just like a Lightning or Hyper Checkpoint)CFG 1 Works with most ResolutionsUse Euler a, LCM, or LCM Karras With this model.Highers Fix 1.5 with Ultrasharp4x UpscalerAdetailer as required Learn More bout it here <a target="_blank" rel="ugc" href="https://huggingface.co/tianweiy/DMD2">https://huggingface.co/tianweiy/DMD2</a>

Pony_V2_DMD2_4S

Pony_V2_lightning_4S ❤Works best with EULER ACFG 1.5Steps 4 , 6 , 8Resolutions:<ul><li>1280x768</li><li>1280x720</li><li>832x1216</li><li>720x1260</li><li>768x1024</li><li>640x1024</li><li>512x768</li></ul>ADetailer RequiredHighers Fix OptionalUpscaler = 4x-UltraSharpSteps = 5+Denoise = 0.2 to 0.3Upscale by = 1.5 and AboveNegative Prompts(Download this negative embedding for best results) <a target="_blank" rel="ugc" href="https://civitai.com/models/177792/negative-embeddingsbystableyogi">Stable_Yogis_PDXL_Negatives</a>Positive Prompts(Download this positive embedding for best results) <a target="_blank" rel="ugc" href="https://civitai.com/models/177792/negative-embeddingsbystableyogi">Stable_Yogis_PDXL_Positives</a>

Pony_V2_Lightning_4s

Pony_V2_Hyper_4S ❤Works best with EULER ACFG 1Steps 4Resolutions:<ul><li>1280x768</li><li>1280x720</li><li>832x1216</li><li>768x1024</li><li>640x1024</li><li>512x768</li></ul>ADetailer RequiredHighers Fix OptionalUpscaler = 4x-UltraSharpSteps = 5+Denoise = 0.2 to 0.3Upscale by = 1.5 and AboveNegative Prompts(Download this negative embedding for best results) <a target="_blank" rel="ugc" href="https://civitai.com/models/177792/negative-embeddingsbystableyogi">Stable_Yogis_PDXL_Negatives</a>Positive Prompts(Download this positive embedding for best results) <a target="_blank" rel="ugc" href="https://civitai.com/models/177792/negative-embeddingsbystableyogi">Stable_Yogis_PDXL_Positives</a>

Pony_V2_Hyper_4S

Babes_Pony_V1_By_Stable_Yogi ❤Discover our versatile new model—the perfect all-rounder for all your image needs! With enhanced body anatomy, hands, colors, and detailed tweaks, it delivers outstanding results every time. Give it a try and you’ll love it!Works best with Euler a, DPM2 a Karras, DPM++ 2M SDE Exponentialare best, you can try others samplers too.CFG 4.5 and aboveSteps 20 and aboveResolutions:<ul><li>1280x768</li><li>1280x720</li><li>1080x720</li><li>832x1216</li><li>768x1024</li><li>640x1024</li><li>512x768</li></ul>ADetailer RequiredHighers Fix RequiredVAE updated on 08-09-2024 to resolve previous issues. Please download the fixed version if you obtained an earlier release.Upscaler = 4x-UltraSharpSteps = 5+Denoise = 0.2 to 0.3Upscale by = 1.5 and AboveNegative Prompts(Download this negative embedding for best results) <a target="_blank" rel="ugc" href="https://civitai.com/models/177792/negative-embeddingsbystableyogi">Stable_Yogis_PDXL_Negatives</a>Positive Prompts(Download this positive embedding for best results) <a target="_blank" rel="ugc" href="https://civitai.com/models/177792/negative-embeddingsbystableyogi">Stable_Yogis_PDXL_Positives</a>=========================================================

PONY_V1_FIX

XL_V2_LIGHTNING ❤Works best with EULERCFG 1Steps 4 Resolutions:<ul><li>1280x768</li><li>1280x720</li><li>832x1216</li><li>768x1024</li><li>640x1024</li><li>512x768</li></ul>ADetailer RequiredHighers Fix OptionalUpscaler = 4x-UltraSharpSteps = 5+Denoise = 0.2 to 0.3Upscale by = 1.5 and AboveNegative Prompts(Download this negative embedding for best results) <a target="_blank" rel="ugc" href="https://civitai.com/models/177792/negative-embeddingsbystableyogi">Stable_Yogis_PDXL_Negatives</a>Positive Prompts(Download this positive embedding for best results) <a target="_blank" rel="ugc" href="https://civitai.com/models/177792/negative-embeddingsbystableyogi">Stable_Yogis_PDXL_Positives</a>

XL_V2_LIGHTNING

BABES_PONY_V1_INPAINTSampler Euler a for Best Results

PONY_V1_INPAINT

Babes_V6_By_Stable_Yogi ❤Discover our versatile new model—the perfect all-rounder for all your image needs! With enhanced body anatomy, hands, colors, and detailed tweaks, it delivers outstanding results every time. Give it a try and you’ll love it!Works best with DPM++ SDECFG 4.5 to 9Steps 18 to 27Minimum Resolution 512-768, 768-512ADetailer RequiredHighers Fix RequiredUpscaler = 4x-UltraSharpSteps = 5 or 9Denoise = 0.1 to 0.2Upscale by = 2For +VE Prompt use these tools<a target="_blank" rel="ugc" href="https://civitai.com/models/582057?modelVersionId=649300">Stable-Yogis-Truecapture-1.5x</a><a target="_blank" rel="ugc" href="https://civitai.com/models/582057?modelVersionId=660182">Stable-Yogis-Rembrandt-lighting-1.5x</a><a target="_blank" rel="ugc" href="https://civitai.com/models/582057?modelVersionId=649323">Stable-Yogis-EtherealBeauty-1.5x</a><a target="_blank" rel="ugc" href="https://civitai.com/models/178167?modelVersionId=622808">&lt;lora:Detail-Slider-V3-By-Stable_yogi:0.4&gt;</a><a target="_blank" rel="ugc" href="https://civitai.com/models/179712?modelVersionId=201677">&lt;lora:NOISEOFFSET_BY_STABLE_YOGI:0.4&gt;</a>For - VE Prompt use these Tools<a target="_blank" rel="ugc" href="https://civitai.com/models/383667/influencer-negatives-by-stable-yogi">influencer-negatives-by-stable-yogi</a>===================================================

V6.0

Babes V5 by Stable Yogi ❤Works best with DPM++ 3M SDE ExponentialCFG 4+Steps 20+Minimum Res 512-768Highers Fix RequiredUpscaler = 4x-UltraSharpSteps = 10Denoise = 0.30Upscale by = 2ADetailer Required

V5.0

Babes V5 LCM by Stable YogiWorks best with LCMCFG 1.5 or 2Steps 10Minimum Res 512-768ADetailer RequiredHighers Fix RequiredUpscaler = 4x-UltraSharpSteps = 5Denoise = 0.35Upscale by = 2For +VE Prompt use these tools<a target="_blank" rel="ugc" href="https://civitai.com/models/582057?modelVersionId=649300">Stable-Yogis-Truecapture-1.5x</a><a target="_blank" rel="ugc" href="https://civitai.com/models/582057?modelVersionId=660182">Stable-Yogis-Rembrandt-lighting-1.5x</a><a target="_blank" rel="ugc" href="https://civitai.com/models/582057?modelVersionId=649323">Stable-Yogis-EtherealBeauty-1.5x</a><a target="_blank" rel="ugc" href="https://civitai.com/models/178167?modelVersionId=622808">&lt;lora:Detail-Slider-V3-By-Stable_yogi:0.4&gt;</a><a target="_blank" rel="ugc" href="https://civitai.com/models/179712?modelVersionId=201677">&lt;lora:NOISEOFFSET_BY_STABLE_YOGI:0.4&gt;</a>For - VE Prompt use these Tools<a target="_blank" rel="ugc" href="https://civitai.com/models/383667/influencer-negatives-by-stable-yogi">influencer-negatives-by-stable-yogi</a>===================================================

V5-LCM

Babes V4 Instagram Edition by Stable Yogi ❤Works best with DPM++ SDE KarrasCFG 4+Steps 20+Minimum Res 512-768Highers Fix RequiredUpscaler = 4x-UltraSharpSteps = 10Denoise = 0.30Upscale by = 2ADetailer RequiredThis is a checkpoint dedicated to delivering unparalleled results for the Instagram Influencer Series.1: Specially Designed for Versatility: Seamlessly integrates with various LoRAs from the influencers series, focusing on Instagram-centric styles, locations, and aesthetics.2: Optimized for Quality and Detail: Trained on a vast dataset of Instagram images to ensure authenticity in style and environment. Effective with both low and high CFG settings.3: Precision in Anatomy and Detail: Expertly generates detailed images with a strong adherence to prompts, capturing the essence of Instagram influencers.4: We Value Your Feedback: Your insights are crucial to the continuous improvement of this model. Please share your experiences and suggestions.There are more Tools and Instagram Influencer Models in this series, check them out<a target="_blank" rel="ugc" href="https://docs.google.com/spreadsheets/d/1NWAWuEpgPPQ6wbOwTDNtPwBA2dUNF3IqEjkV1dlWAIM/edit#gid=0">Link here</a>&lt;====END====&gt;

V4-Instagram-Edition

Babes_XL_V1Works best with DPM++ 3M SDE ExponentialCFG 5+Steps 20+Minimum Res 512-768 and 680-1024

XL_V1

Babes_XL_V1_LCMWorks best with LCMCFG 1.5+Steps 8+Minimum Res 512-768 and 680-1024

XL_V1_LCM

Realistic and Beautiful Images ,Good Hands, and less Noise.Configuration is BelowCFG 1Steps 8+Resolution 512-768, 576-864AdetailerHigh res Fix is optional,Hires Steps 5Upscale by 1.2Upscaler NMKD FacesDenoise 0.2

V3+LCM

Realistic and Beautiful Images , Good Hands, and less Noise. Configuration is Below CFG 7 Steps 20+Resolution 512-768, 576-864Adetailer High res Fix is optional, Hires Steps 5 Upscale by 1.2 Upscaler NMKD Faces Denoise 0.2

Type	Checkpoint Trained
Stats	12,515 119.3k 242.4k
Generation
Reviews	Overwhelmingly Positive (1,051)
Published	Aug 14, 2025
Base Model	Pony
Hash	AutoV2 CFB4D11B6F