Upload 74 files

.gitattributes

@@ -33,3 +33,17 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Artworks/Atla_Style_Z-Turbo.jpg filter=lfs diff=lfs merge=lfs -text
+Artworks/dovilio_brero_Atlantis_.jpg filter=lfs diff=lfs merge=lfs -text
+Artworks/pictaevum_v2_de-turbo.jpg filter=lfs diff=lfs merge=lfs -text
+Artworks/Vector_Paintings_ZIT.jpg filter=lfs diff=lfs merge=lfs -text
+Characters/Fantasy/nightelf_v1.jpg filter=lfs diff=lfs merge=lfs -text
+Creative/elegence-niji-z.jpg filter=lfs diff=lfs merge=lfs -text
+Illustration/Nicolas_Roerich_v4_zimage.jpg filter=lfs diff=lfs merge=lfs -text
+NSFW/face_forward_Look_back-Z_v1.jpg filter=lfs diff=lfs merge=lfs -text
+NSFW/handgoo_grabbing_hands.jpg filter=lfs diff=lfs merge=lfs -text
+NSFW/luisa_female_nudism_v2.jpg filter=lfs diff=lfs merge=lfs -text
+NSFW/Perky_Tits.jpg filter=lfs diff=lfs merge=lfs -text
+NSFW/saggers_by_deedeemegadoodo_zimage_v1.jpg filter=lfs diff=lfs merge=lfs -text
+NSFW/SteepSlopeTiddies_XXL_ZIT.jpg filter=lfs diff=lfs merge=lfs -text
+NSFW/zentai1.jpg filter=lfs diff=lfs merge=lfs -text

Artworks/Arcane_style_2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa743e979716bddd0cee41fea2ab46e9398bc7a98810bfd6695cdb75f5008e03
+size 170127768

Artworks/Arcane_style_2/info.txt

@@ -0,0 +1,7 @@
+NO TRIGGER WORD :
+Arcane-Inspired LoRA Model.
+Recommended Usage:
+
+Checkpoint: Zimage base / Zimage turbo / Zimage Edit
+
+Strength: 0.80 ( best setting

Artworks/Atla_Style_Z-Turbo.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c59b76e0863379f52c40c2409fdcfd9383f6441eef0ec22235b1d56547c0612
+size 170128232

Artworks/Atla_Style_Z-Turbo/info.txt

@@ -0,0 +1,35 @@
+This model was trained using extremely low resolution screenshots of the show "Avatar The Last Airbender" as I was getting some pretty severe artifacts when attempting to upscale.
+
+I'd reccomend a weight of 1 generally I've found that the range .9 (To fix character generations) and 1.15 (To force style) tend to work alright.
+
+V1 Notes
+This lora was not trained using any of the names of the character's within the show and therefore will not know the characters implicitly.
+
+Strengths and weaknesses
+Strengths:
+
+Decent quality environment and background
+
+Weaknesses:
+
+Strongly conforms to any stylistic tags in the prompt. (If you prompt for photorealism, you'll get photorealism)
+
+Struggles with characters in a variety of ways.
+
+Tries to render the characters in the same high detail manner of the environments in close-up shots
+
+Completely distorts the characters from a distance
+
+Tends to close the eyes of the characters without being prompted to do so.
+
+Prompt notes
+
+If you'd like to see some bending you can use the following prompt scheme:
+
+{subject} casts fire from their hands.
+
+{subject} is casting a spell causing water to swirl around them violently.
+
+{subject} is casting a spell that causes the boulder to levitate.
+
+etc.

Artworks/Jacques_Louis_David_V1_ZImage_Turbo_JGF.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0500725c145fe6bd76fea56124681b9a55aef2cb6cd746450787b69db568a98f
+size 170128240

Artworks/Jacques_Louis_David_V1_ZImage_Turbo_JGF/trigger.txt

@@ -0,0 +1,122 @@
+Overview
+David_V1_ZImage_Turbo_JGF is a pictorial-style LoRA  designed to bring your images closer to the French neoclassicism of Jacques-Louis David: clean contours, solemn historical scenes, heroic figures, theatrical lighting and a feeling of "oil on canvas" with marked brushstrokes when requested.
+
+He is trained with Z-Image Turbo in mind, where he excels especially in portraiture, historical scenes, figures on horseback, and classical composition from the late eighteenth and early nineteenth centuries.
+
+When does this LoRA shine?
+
+It works especially well when the scene fits with what David would have painted:
+
+Solemn portraits, half- or full-length characters.
+
+Historical, military or political scenes.
+
+Figures on horseback, heroic compositions, theatrical poses.
+
+Interior atmospheres with curtains, columns, classical architecture.
+
+In these cases, with a moderate power around 1.00 the model usually works very well:
+
+Clean drawing and classical anatomy.
+
+The lighting is clear and orderly, without stridency.
+
+The palette of French neoclassical oil painting.
+
+Pain points and how to compensate for them
+
+Landscapes: Jacques-Louis David only has one landscape in his work, so the LoRA is short of reference in purely landscape scenes.
+
+In these cases it is advisable  to force the power to 1.30 or more and make it very clear in the prompt that you want a box:
+
+«oil painting», «art», «painting», «oil on canvas», «bold brushstrokes», «painterly texture», etc.
+
+Scenes far removed from David's world (science fiction, very modern fantasy, contemporary aesthetics, etc.)
+
+The style is marked, but you have to push:
+
+Use high powers (1.30).
+
+He always reinforces the idea of an oil painting in the text.
+
+Large groups of people: groups are regular.
+
+In scenes with many figures he tends to lose some control in faces and hands.
+
+It's best to focus on 1–4 main characters, at most up to 7.
+
+Recommended settings
+LoRA Power
+
+Recommended range: 1.00 – 1.40.
+
+Usual sweet spot: around 1.30.
+
+For scenes that are not typical of David (landscapes, science fiction, etc.):
+
+Raise to 1.30  and reinforce with painting words.
+
+Resolution (in Z-Image)
+
+It can be climbed until 2048, but:
+
+1024 is still Z-Image's sweet spot, very stable.
+
+1536 usually gives a good combination of detail and consistency.
+
+2048 is possible, but with a little more instability depending on the scene.
+
+Sampler and scheduler
+
+Euler works well from the base.
+
+With res_2s the quality improves.
+
+With res_5s it improves even more at the cost of killing speed.
+
+Scheduler recomendado: beta57.
+
+Steps and high resolution
+
+A very balanced scheme:
+
+9 steps in the main generation.
+
+4 steps in the "highres fix" with denoise ≈ 0.35.
+
+(If you're in a hurry, the LoRA works even with 2 steps using Euler or 2m, although you'll obviously lose some finesse.)
+
+Denoise and style
+
+To strongly mark the painting style, a denoise (0.90) can help the model give more painterly character by omitting the final cleanup.
+
+DPM++ 2M Karras can sometimes give a particularly beautiful, softer paint finish with a very nice classic touch.
+
+Prompt Tips
+
+Although this LoRA does not depend on a specific "trigger word", it helps, especially when the subject does not fit with David's painting:
+
+Include some indication of the pictorial medium:
+
+«oil painting», «classical painting», «art», «oil on canvas», «bold brushstrokes», «painterly texture».
+
+Remember the historical context in the description:
+
+«18th century», «French neoclassical painting», «Revolution era», «Napoleonic portrait», etc.
+
+Order Heroic Poses and Classical Composition:
+
+«heroic pose», «dramatic lighting», «theatrical composition», «neoclassical architecture in the background».
+
+Summary
+David_V1_ZImage_Turbo_JGF is a LoRA designed for those looking for a French neoclassical style à la Jacques-Louis David, with an emphasis on:
+
+Portraits and historical scenes.
+
+Classical composition, heroic figures, solemn atmospheres.
+
+Oil texture and marked brushstroke when asked.
+
+Its sweet spot is around 1.30 power, resolutions between 1024 and 1536, and a flow of 9 steps + smooth highres fix. Outside of David's typical iconography (especially in landscapes and very modern scenes) he asks for a little more strength in weight and text so that the style prevails.
+
+Have fun!

Artworks/Vector_Paintings_ZIT.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6897e2d0948d7cd6ed8dc34e59f338f3447a203fe75ea0826ef5ab62dde1e1e
+size 170128312

Artworks/Vector_Paintings_ZIT/trigger.txt

@@ -0,0 +1,32 @@
+VectorPaintDaal
+
+
+-----
+
+
+🖌️ Vector Paintings
+Keyword: VectorPaintDaal
+Recommended Strength: 0.5–1.5 (Best at 1.0) for Flux
+
+Illustrious recommended strengths 1.0 to 1.5 works best at 1.3 somewhat subjective.
+
+🎨 Where Vector Meets Emotion
+Vector Paintings is a stylistic LoRA that fuses bold vector shapes with an expressive painterly overlay—resulting in vivid images brimming with color, character, and emotion. Think clean lines meets emotional brushwork, with a sense of motion, light, and whimsy woven into every scene.
+
+This LoRA shines with people, creatures, urban scenes, fantasy beasts, and emotion-rich environments. Whether you're painting a rainbow-haired barista, a whimsical flying whale, or a joyful monster barreling through the woods, this LoRA captures the energy and emotion of the moment with the storytelling power of impressionist brushwork layered over modern vector design.
+
+The result? A stylized world that feels animated yet artistic, structured yet emotional. It’s especially great for conveying joy, wonder, mystery, or nostalgia—ideal for storytellers and illustrators alike.
+
+🧠 How to Use It:
+Use VectorPaintDaal in your prompt to trigger the style.
+
+Works best at 1.0, but experiment between 0.5 to 1.5 for more subtle or intense stylization.
+
+Works well with single-subject prompts or narrative settings that emphasize light, motion, or a core feeling.
+
+Avoid ultra-photorealistic or heavily literal prompts—this LoRA thrives on creative expression and storytelling tone.
+
+💬 Add to the Colorful Conversation!
+If you like what you create, give it a thumbs up and share your first image on the LoRA page. Your creations bring the model to life, spark new inspiration, and help keep this vibrant community growing.
+
+Let's keep the brush strokes flying. 💫

Artworks/dovilio_brero_Atlantis_.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:268a11d7dec7e7b5ec7a8405749d47d82fe4b3548f9bf360ac2227265469526f
+size 170128304

Artworks/dovilio_brero_Atlantis_/trigger.txt

@@ -0,0 +1,16 @@
+dovilioatlan
+dovilioatlan style
+
+
+recommended to use words like "surreal," "illustration," "painting," etc.
+
+----
+
+
+Attempt to recreate the style of the Italian painter Dovilio Brero.
+
+You can get more or less realistic images depending on how you use your prompt, or whether it's short or long.
+
+Trigger: dovilioatlan style
+
+It's recommended to use words like "surreal," "illustration," "painting," etc.

Artworks/pictaevum_v2_de-turbo.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f20227c60c08377db5cf97e12c28dd4632770ebf87d359978bf77301b705ca
+size 170128224

Artworks/pictaevum_v2_de-turbo/info.txt

@@ -0,0 +1,4 @@
+Based on the style of Clyde Caldwell.
+
+Trained on Z-Image-De-Turbo
+It's trained with "pictaevum_style" in the captions, but it doesn't seem to make a big difference.

Characters/Fantasy/nightelf_v1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098124cf5da443801cb6068d3b85c7c15d936fec4b32d312135c1bd8419f810a
+size 170128240

Characters/Fantasy/nightelf_v1/trigger.txt

@@ -0,0 +1,11 @@
+ifanightelf
+long eyebrows
+long pointy ears
+
+--------
+
+I present the Zimage Nightelf Lora. It uses the trigger-word ifanightelf
+It is also trained on "long eyebrows, long pointy ears, facial markings". It also responds quite well to "glowing <color> eyes" and "<color> sclera"
+
+This is one of my first lora, but I think it has turned out half decent. I trained it using ai-toolkit. I trained to 3500 steps.
+I have left the workflows attached to my images.

Characters/Games/ballerina_twin_from_atomic_heart_Z.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55757b56368fb05bce568233b33946c4a6c12cb024a85f06317b7faa92d18cd6
+size 170127768

Characters/Games/ballerina_twin_from_atomic_heart_Z/trigger.txt

@@ -0,0 +1,10 @@
+ballerina_twin_from_atomic_heart, robot girl, red_star_on_forehead, metal skin, faceless, crown braid, blonde hair, metallic shine, colored skin, robot joints,
+
+yellow jacket, cropped jacket, open jacket, sleeves rolled up, featureless crotch, featureless breasts,
+
+
+---
+
+A highly detailed robotic twin ballerina from Atomic Heart, a feminine photorealistic image with a futuristic style, smooth metallic skin with a bright metallic sheen, a featureless reflective face highlighted by a crown braid hairstyle with loose blonde hair on her forehead – a bright red star, painted metallic leather with smooth transitions and reflections of light,
+a girl holding the thick stem of a large, vibrant red rose close to her face, bringing it delicately to her face in a tender, poetic gesture. Close-up portrait with a cinematic composition featuring intricate details, elegant pose, and refined beauty. Highly detailed with symmetrical facial features, soft skin textures, and luminous eyes. Embodying a magical, dreamlike atmosphere with a radiant glow and mystical ambiance. Sharp focus capturing every nuance of her expression, majestic presence, and flowing hair. Overall composition is very coherent, artistic, and visually stunning, with dramatic, warm lighting emphasizing her features and the rich, deep colors of the scene. The background is flawlessly designed, adding an ambient, atmospheric touch without distracting from the main subject. Set details are carefully tailored, combining a lush, richly textured environment with an ornate, professional backdrop, creating a perfect, immersive visual experience.
+

Creative/elegence-niji-z.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd6ec854d3a8a298a6341d8a84ddc2b160449d10406aa14ee143ce9b8ed997e
+size 170127768

Creative/elegence-niji-z/trigger.txt

@@ -0,0 +1,20 @@
+3l3ganc3
+
+
+-----
+
+ZIT Weights : 0.8 -1.2
+
+
+So added the ZIT version, I am very happy with the results even with training on a much smaller data set, there as still a few issues and my prompting style is a mess (sorry i am new to natrual language prompting) one of the things i am trying to fix in possible future versions is reducing the very warm coloring this lora defaults to (you can brute force it with prompts if you want).
+
+Please feel free to share your feedback, I am still trying to refine it :)
+------------------------------------------------------------------------------------------------
+Illustrious Weights : 1 -1.6
+
+
+This is lora was designed to replicate some the niji 6 realistic anime/draw art style, the data set mostly focused on portraits for male and female but you can brute force it for more dramatic poses.
+
+Some of the features can be triggers using prompts like "3l3ganc3, realistic, semi-realistic" etc..
+
+I have tried it with several illustrious/SDXL/Pony models and it seem to works well flat anime style as well as more 3d styles (though it intended more for the former, I shall update more resources that work with it as I discover them myself)

Illustration/Czechoslovakian_matchbox_trigger_s0r3l4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20afba8b27a768aac7f19cf7b54ef639b9e1d4108e384b3c612d6e6c66776b10
+size 170128296

Illustration/Czechoslovakian_matchbox_trigger_s0r3l4/trigger.txt

@@ -0,0 +1,31 @@
+s0r3l4
+flat geometric illustration of
+limited color palette
+vintage print texture
+
+----
+
+
+Czechoslovakian Matchbox Style
+This style captures the distinctive graphic design of matchbox labels produced in Czechoslovakia during the mid-20th century. These small-scale artworks became a unique canvas for official propaganda, folk motifs, industrial pride, and everyday life.
+
+Characterized by bold flat colors, simplified geometric forms, and clean linework, these labels often featured stylized depictions of factories, landscapes, workers, children, animals, and socialist symbols. The limited color palettes and screen-printing techniques gave them a tactile, vintage quality that blended modernist principles with folk art traditions.
+
+Though born from a planned economy, these matchbox designs became an unintentional archive of national identity, visual culture, and quiet creativity under socialism. This LoRA recreates that vibrant, nostalgic, and graphically rich world, perfect for generating illustrations with a retro, Eastern Bloc charm.
+
+Usage Instructions
+This upload includes two LoRA variants for flexible creative control.
+
+Czechoslovakian Matchbox Style with trigger word
+
+Trigger word: s0r3l4
+
+Use this prompt format for your generations:
+
+s0r3l4 flat geometric illustration of <your prompt>, limited color palette, vintage print texture
+
+This version produces richer details, stronger stylistic adherence, and a more authentic vintage graphic look. Note: When generating celebrities, results will lean toward photorealistic portraits.
+
+Czechoslovakian Matchbox Style without trigger word
+
+No trigger word needed. This version emphasizes simplified shapes, bolder geometry, and flatter color fields. It works better for rendering celebrities in a stylized, illustrative manner. Closer to vintage graphic portraits than photos. Mentioning " flat geometric illustration", "limited color palette" and "vintage print texture" can help with better generations.

Illustration/Kirkbride-ZIT.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22715cb9405a37e4b882ab87c726513168d5625599e4992820c7f6349b127cb7
+size 170127768

Illustration/Kirkbride-ZIT/info.txt

@@ -0,0 +1,9 @@
+Michael Kirkbride is a former designer and writer for Bethesda Softworks, primarily known for his works influencing the game Elder Scrolls III: Morrowind, but for lore contributions to subsequent titles in the franchise as well.
+
+This LoRA was trained on upscaled and manually adjusted examples of his works.
+
+Z-Image Turbo
+
+Testing was done locally in forge-neo with LCM sampling and Normal scheduling, at CFG 1-1.2 with 10 Steps.
+
+Hires settings were with Remacri-Original at 1.5 Scaling, 0.65 Denoising, CFG 1.5 with 10 Steps.

Illustration/Nicolas_Roerich_v4_zimage.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf30b91d601bb64ba94a0704d9d1376084be33c557afd8e8a80658e6978833f7
+size 170128304

Illustration/Nicolas_Roerich_v4_zimage/trigger.txt

@@ -0,0 +1,14 @@
+nicholas roerich's painting of 
+
+
+----
+
+A style LoRA trained on public domain art of Nicholas Roerich
+
+sample prompt:
+
+a painting in style of Nicholas Roerich
+
+Nicholas Roerich's painting of (something appropriate)
+
+Nicholas Roerich's (something)

NSFW/Hard_erect_Long_Nipples_v1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:401889d9b8597b45852e0f24ce7a293c4250146d752417534ef67e4d777fe7fc
+size 170128224

NSFW/Hard_erect_Long_Nipples_v1/info.txt

@@ -0,0 +1,13 @@
+This lora will produce hard erect nipples for images made with Z-Image Turbo.
+
+Normal ZIT settings (low steps/cfg, euler/normal or euler/simple) work well.
+
+Seems to work on any age, breast size and body type.
+
+Starts working well around 0.5 until around 0.9ish where it degrades the rest of the image.
+
+Works best on its own, but can be used with other loras at low range seems to work if you tweak both loras until you're happy.
+
+Shout out for AITools/Ostris training app.
+
+Cheers

NSFW/Perky_Tits.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:003a85aa67044c517d3d09e554d771ac835070be9dc5c61e9adc5d4f7bbd98e4
+size 170128216

NSFW/Perky_Tits/info.txt

@@ -0,0 +1,2 @@
+Perky Tits for Z Image Turbo - an attempt to improve female body appearance with better breasts.
+

NSFW/SEAN_ARCHER_Glamour_Photographer.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89d32c932c157878fdad3cd395597f619b21b3264b61b359d5b0856808d63c75
+size 170128216

NSFW/SEAN_ARCHER_Glamour_Photographer/info.txt

@@ -0,0 +1,9 @@
+(+)
+<lora:SEANARCHER:0.5>, This is a high-resolution photograph featuring a young woman in a contemplative pose against a textured, dark gray background. The subject has fair skin and long, straight, light brown hair that is styled in a loose, single braid draped over her right shoulder. She is wearing an oversized, unbuttoned gray shirt that hangs loosely over her shoulders, revealing her bare midriff and a black elastic bracelet on her left wrist. She is also wearing a pair of light brown, loose-fitting pants that rest low on her hips. Her expression is introspective, with her eyes gazing downward and her lips slightly parted. The lighting is soft and moody, casting gentle shadows that accentuate the contours of her body and the texture of her clothing. The background is a plain, dark gray wall with a subtle gradient, adding depth to the image without distracting from the subject. The overall atmosphere is serene and intimate, emphasizing the subject's vulnerability and inner thoughts.( The bottom left corner of the image has the text "SEAN ARCHER" in small, white letters:1.4)
+
+
+
+<lora:SEANARCHER:0.5>, This is a high-resolution photograph featuring a young woman posing in a provocative yet tasteful manner. She is seated on a dark brown, leather-like surface, with her right knee bent and her left leg extended, highlighting her toned physique and curvaceous figure. She has a light skin tone and is of Caucasian ethnicity. Her blonde hair is styled in a messy, half-up, half-down do, with loose strands framing her face., She is wearing a white, ribbed, sleeveless crop top that clings to her slender frame, revealing her flat stomach and small breasts. The top has a lace-up front, adding a touch of sensuality. She pairs the top with matching white panties, which accentuate her hips and buttocks., The woman's expression is serious, with a slight pout, and she gazes directly at the camera, creating a sense of intimacy. Her body language is confident and relaxed, with her right hand resting on her thigh and her left hand lightly touching the surface behind her., Her right arm displays a large tattoo of a floral design, and another tattoo is visible on her left forearm. The background is a textured, dark brown wall, which contrasts with her light attire, drawing attention to her form. The photograph has a moody(The bottom left corner of the image has the text "SEAN ARCHER" in small, white letters:1.4)
+
+
+<lora:SEANARCHER:0.5>, Baroque-inspired studio nude in hyperrealistic detail. A mature woman in her late 40s with olive skin, silver-streaked dark hair pulled into a low bun, and soft, lived-in curves stands with arms loosely crossed below her bust — not defensive, but composed. Her face shows quiet wisdom: slight lines around the eyes, relaxed mouth, gaze meeting the viewer without challenge or submission. Lighting: dramatic Rembrandt triangle on the face, warm amber glow tracing the spine and outer thighs. Natural pubic hair rendered as a soft, shadowed mass consistent with her body’s tonal logic. Background: absolute darkness. Fabric absent; only the body, light, and air. High-resolution skin texture, subtle venous detail, emotional gravity

NSFW/SteepSlopeTiddies_XXL_ZIT.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cc82977bddc3c787f721aa72afa6d237446f4e336f58325c40d56f8e864dcc0
+size 170128320

NSFW/SteepSlopeTiddies_XXL_ZIT/trigger.txt

@@ -0,0 +1,23 @@
+SteepSlopeTiddies
+
+-----
+
+Z-img Turbo XXL Version:
+This is my first ZIT LoRA so hopefully there aren't any glaring issues but let me know if you notice anything. 0.75 was the approx. strength that I landed on but feel free to experiment!
+
+XXL Version:
+Added to, subtracted from, and manually modified the existing v1.2 dataset for that bigger impact. Purely a preference version compared to v1.2 if you like em big or really big. The closer you get to 1.0 strength the more likely alpha shapes will appear and the head will be out of frame. A strength of 0.75 seemed to be a good spot, but if you're ok with wading through some garbo gens, 1.0 will give you the biggest knockers.
+
+----
+
+(+)
+HD portrait photo of a gorgeous redhead woman. She is sitting at her office desk completely nude, her swooping breasts large and perfect. Her nipples are slightly puffy and perfect.
+
+
+HD full body photo of a gorgeous Korean woman. She is grocery shopping at the grocery store completely nude, her swooping breasts large and perfect. Her nipples are slightly puffy and perfect.
+
+
+HD full body photo of a gorgeous Russian brunette supermodel. She is posing for a photoshoot at different famous landmarks, her swooping breasts large and perfect. Her nipples are slightly puffy and perfect.
+
+
+HD portrait photo of a gorgeous redhead woman. She is laying on her bed completely nude, her breasts large and perfect. Her butt is big and athletic, as if squats are a focus in her workout routine.

NSFW/doggystyle_pov.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a8411198d8b2e8a7e1fcd280b173894ba2bf2b97c6ac1bbee505bab6e407358
+size 340194528