Added the ability to create and edit tags for LoRA

2026-07-23 15:29:12 +03:00
parent 3a14e97a3e
commit 86ee243b80
1111 changed files with 12386 additions and 4 deletions
@@ -0,0 +1,10 @@
+{
+  "hash": "0040545e6da0bbd3d1633e1d6ba28c0048f0be42ec60e1d3feec3a442480f95a",
+  "name": "[FLUX.2-klein-9B] Airbrush it! LoRa [STYLE]",
+  "trained_words": [
+    "Turn this into arbzh style"
+  ],
+  "description": "Highly recommend using it on CivitAI's generator (1 - 1.4 strenght) Base prompt: Turn this into arbzh style Dataset: 100 images okay so i kinda left this account abandoned for like 3 months because of work and life stuff, and honestly i still can’t guarantee i’m fully back because i don’t have that much time right now. but anyway, i wanted to share this LoRa i made because i really like this nostalgic airbrush style. it can basically take almost any image you like and push it into that soft glossy retro airbrush look, with the creamy highlights, smooth gradients, and that kind of old poster / early digital illustration feeling. Some of the images in the preview were made locally and a few are examples i got from the Civit generator so results may vary in terms of quality.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:17:26.688726"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "005cff1956c158c3968e02330083070f2b20f379c9530cb4e089c535b18c9ae7",
+  "name": "Thomas Haller Buchanan",
+  "trained_words": [
+    "Art by Thomas Haller Buchanan"
+  ],
+  "description": "Thomas Haller Buchanan is an American artist and illustrator known for his versatile and detailed work. Early in his career, he trained as a combat artist in the U.S. Army and later honed his skills in a commercial art studio. His art often reflects an early 20th-century fantasy aesthetic, blending realism with texture and design. Buchanan has worked on a wide range of projects, including portraits, murals, and educational exhibits for museums and institutions. NOTE : Base model : Z Image Turbo &amp; Flux1 . Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow. IMPORTANT NOTE : This model is a tribute to the artist and not an attempt to copy or reproduce his works. VERY IMPORTANT NOTE : Do not like my models, do not give me buzz, do not follow me, otherwise you will be reported to Civitai for attempted corruption",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:53:41.305171"
+}
@@ -0,0 +1,18 @@
+{
+  "hash": "00674ab0e236f178f726d3bea7e20dc7cb15c7b23b57362007bb6e5aa50f3b48",
+  "name": "HiDream meets FLUX 👀 (FLUX v0.1)",
+  "trained_words": [
+    "aidmaHiDreamStyle",
+    "detailer",
+    "anime",
+    "photo",
+    "concept",
+    "woman",
+    "details",
+    "model",
+    "realistic"
+  ],
+  "description": "v0.1 strengh comparison",
+  "source": "civitai",
+  "imported_at": "2026-07-23T14:51:51.996746"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "00b3b5fa48f98280ba3764531f904f46f759d0fb5063d04c72f934fb2901fd8d",
+  "name": "Alexey Egorov",
+  "trained_words": [
+    "Gorovalex art style"
+  ],
+  "description": "Alexey Egorov is a contemporary digital artist known for surreal, symbolic compositions that blend ritualistic imagery with sculptural forms and muted palettes. His work often explores solitude, transformation, and metaphysical tension through enigmatic figures and abstract environments. NOTE : Base model : Z Image Turbo &amp; Flux1 . Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow. IMPORTANT NOTE : This model is a tribute to the artist and not an attempt to copy or reproduce his works. VERY IMPORTANT NOTE : Do not like my models, do not give me buzz, do not follow me, otherwise you will be reported to Civitai for attempted corruption",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:17:34.763212"
+}
@@ -0,0 +1,19 @@
+{
+  "hash": "00d7af617872d694eab5c92a409c6150ef705145f1bd5a4b058f349de22c647e",
+  "name": "Ink Paint Splash Artwork Style [FLUX] (FLUX)",
+  "trained_words": [
+    "aidmainkstyle",
+    "3d",
+    "ink",
+    "painting",
+    "style",
+    "artwork",
+    "design",
+    "paint",
+    "splash",
+    "logo"
+  ],
+  "description": "v0.1",
+  "source": "civitai",
+  "imported_at": "2026-07-23T14:52:43.574771"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "01345e1866a121b8745166e79e92f58812f8c903fd9a0a8d1ba5c031642563cf",
+  "name": "Dark Art Painting \"Realistic\" Style XL + F1D",
+  "trained_words": [
+    "dark art movement style"
+  ],
+  "description": "Update : Please if you see any of my models somewhere else report or let me know! Thnx Trained on base model xl 1.0 + F1D Works well with realistic stock photo model. Feedback and ratings are much appreciated. Feel free to check other models: Pawel Kuczynski art style Dark Painting - Chiaroscuro Lighting style Frank Frazetta Art style Pawel Kuczynski art style The Fallen Angel Painting style by (Alexandre Cabanel)",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:27:55.692465"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "01a43a575251b6260a153c114d8847907cfabb06d843693adb337d4c40905c2f",
+  "name": "Wally",
+  "trained_words": [
+    "Nogeleschie art style"
+  ],
+  "description": "Model inspired by Egon Schiele, Edoardo Tresoldi &amp; Paul Cadmu. As a female figure, the model was trained in several images of Egon Schiele's principal muse and companion, Walburga Neuzil, nicknamed \"Wally\". Model and lover between 1911 and 1915, she profoundly influenced his work, inspiring many intense expressionist nude portraits, including the famous \"Portrait of Wally\" (1912). NOTE : Base model : Z Image Turbo Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:55:08.842242"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "020aa9dd5576675dd4db9687ed37b068361c31da0b344230526d63e444783e40",
+  "name": "Terry & Rachel Dodson",
+  "trained_words": [
+    "TeRachedon style"
+  ],
+  "description": "Terry Dodson is a renowned American comic book artist known for his dynamic, expressive linework and elegant character designs. He has illustrated major titles for Marvel and DC Comics, including Wonder Woman , X-Men , and Harley Quinn . His style blends classic comic aesthetics with a modern, polished flair. Rachel Dodson , his wife and longtime collaborator, is a talented colorist whose rich, vibrant palettes bring Terry’s illustrations to life. Her work enhances mood and depth, contributing to the signature look of their joint projects. Together, they form one of the most celebrated artistic duos in contemporary comics. NOTE : The length of the prompt influences the expression of the model, the shorter the prompt, the more the model expresses itself. Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow. All licensing conditions for the Flux Dev model apply. You can find the details here . IMPORTANT NOTE : This model is a tribute to the artist and not an attempt to copy or reproduce his works. Flux1.D is unable to reproduce a graphic universe on which it was trained, the goal is solely to expand Flux's pictorial capabilities. VERY IMPORTANT NOTE : Do not like my models, do not give me buzz, do not follow me, otherwise you will be reported to Civitai for attempted corruption",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:53:38.179911"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "022efd4d826423acac2ad4e16c35d57ff923d5c255a57dbae9d7a11c4cf011c8",
+  "name": "Tanin : Resonance",
+  "trained_words": [
+    "Tanin"
+  ],
+  "description": "Tanin fits modern fashion and editorial moods where subtlety wins.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:53:30.343655"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "02574e48a7e01ba3b54516db1ff9d9ddf179617e7d6b0c6c7305d4d656b489ef",
+  "name": "Comic Book | Tome 3",
+  "trained_words": [
+    "ComFact_V3 art style"
+  ],
+  "description": "NOTE : Base model category: ZImageTurbo &amp; Flux1 . Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:26:53.037129"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0257cb054a2c32f69292fdd9e4383daecbe9cdf3556ecba60b527dec3a3b1548",
+  "name": "Neo-Art Nouveau",
+  "trained_words": [
+    "nartnveauCE_style"
+  ],
+  "description": "It's all about the frame/border, with a somewhat Art Nouveau style.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:45:21.841977"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0272691271026f614af739d5c0158988a12857136cabc123b872e3af6358671a",
+  "name": "Egyptian_WalkLikeOne",
+  "trained_words": [
+    "wlae86"
+  ],
+  "description": "Description: This LoRA brings the rich and visually stunning world of Ancient Egypt to life. It covers a wide range of subjects, from majestic pharaohs and powerful gods to priestesses, mummies, temples, pyramids, and hieroglyphic-filled scenery. The model captures the iconic aesthetics of Egyptian mythology, blending gold, turquoise, lapis lazuli, ornate jewelry, and elaborate costumes into highly detailed images. With this LoRA you can create: Highly detailed character portraits Cinematic scenes set in ancient temples or deserts Epic depictions of Egyptian gods and goddesses Fantasy, horror, or adventure themed compositions Stylized or realistic interpretations depending on your settings The model supports a wide range of styles, from highly realistic to slightly stylized or fantasy-oriented looks, while keeping the recognizable Egyptian essence intact. 🔑 Key Trigger Words ThemeTrigger Words egypt, ancient egypt, egyptian, pharaoh, pyramid, temple, hieroglyphs, desert , nile, god/goddess, anubis, bastet, horus, seth, osiris, isis, apophis, thot, mummy, bandages, wrapped, glowing eyes, priestess, high priestess, royal headdress, ornate jewelry, golden jewelry, lapis lazuli, turquoise gems, ornate necklace, arm cuffs, headpiece, temple columns, hieroglyphic pillars, pyramids in background, ancient ruins, cinematic lighting, divine aura, mystical, desert sunset, dramatic lighting, khopesh, spear, bronze Also trained some places with names. Try around ;) 🖼 Prompt Examples Example 1 – God Anubis (Realistic Heroic Style): anubis, egyptian god, jackal head, muscular male, golden armor, ornate jewelry, egyptian temple background, hieroglyphic pillars, cinematic lighting, ultra detail, sharp focus Example 2 – Egyptian Priestess (High Fantasy Style): egyptian priestess, beautiful young woman, elaborate golden headdress, lapis lazuli jewelry, ornate necklace, arm cuffs, flowing white dress, pyramids in background, divine aura, soft sunlight, ultra detail, cinematic Example 3 – Mummy Horror Scene: egyptian mummy, ancient tomb, glowing eyes, wrapped in bandages, golden amulet, sandstorm, pyramids in distance, horror atmosphere, dramatic lighting, ultra detailed Example 4 – Gods Ensemble (Epic Group Scene): anubis, bastet, horus, isis, osiris, egyptian gods ensemble, standing in grand temple, ornate golden costumes, hieroglyphic walls, giant pillars, cinematic lighting, ultra detail 🔧 Recommended Settings LoRA Weight: 0.7 – 1.0 Works well with: SDXL 1.0 base models, Realistic/Photorealistic checkpoints, Fantasy &amp; Stylized models. Sampler: DPM++ 2M Karras recommended. Resolution: Best results at 1024x1024 or higher. Anything you find of mine outside of Civitai is shared without my permission. Please do not reupload my files. Just link people to my Civitai profile instead. Thanks :) https://civitai.com/user/tehalex86",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:30:01.896898"
+}
@@ -0,0 +1,16 @@
+{
+  "hash": "027583b3737b59e45ae257038cc12ae7813d55a52a36552197d622ac48ca06d3",
+  "name": "Stained Glass and Metal - CE",
+  "trained_words": [
+    "people",
+    "colorful",
+    "glass",
+    "scenery",
+    "metal",
+    "style",
+    "stained glass"
+  ],
+  "description": "Please share your creations. I would love to see how you have used the LoRA. The Stained Glass and Metal LoRA was trained on images with brass and stained glass to produce a particular style, characterized by colorful elements and metallic highlights. Lower weights allow other features to appear more easily, such as people, faces, creatures and so on. V04 is capable of producing brighter images with improved detail.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:52:53.953371"
+}
@@ -0,0 +1,16 @@
+{
+  "hash": "0278852130a587a6001a904a890474e3b5c04fcd715c0be62870d2eb2b2279c9",
+  "name": "NSFW Helper Slider - Krea2",
+  "trained_words": [
+    "slider",
+    "tool",
+    "undress",
+    "naked",
+    "helper",
+    "nsfw",
+    "loraholic"
+  ],
+  "description": "NSFW Helper Slider To make it easy to understand when to use til LoRA, and what it helps with, i made two lists. This is not the same as the \"Refusal-Reduction\" and should not be compared againt eachother. Instead you should use them together to get the best of both worlds. Refusal-Reduction makes the model do what you tell it, while this LoRA make the NSFW stuff look appealing. Recommended range: -1.0 to 5.0 What this LoRA help with: Works in both directions: more NSFW or more SFW Remove/Add clothes Makes it easy to \"roll up\" tops, pull down panties etc. Makes poses more/less exposing and sexual with pos/neg Help with penetration, especially when used with penis size LoRA etc. Better prompt adherence on NSFW details Does minimal changes to rhe image at values below 2.5, compared to alternatives From 2.5 to 5.0 it will take more controll over pose, camera etc, often in a good way. Makes it super easy to use original checkpoints for NSFW images MUCH less changes to the original image compared to Bypass, by a large margine Can make NSFW LoRAs look way more realistic with a small negaitve value like 0.5 What this does NOT do: It will not make non NSFW checkpoints have better looking genital s etc It will not undress people reliably if the prompt states they are dressed It will not undress people reliably if the prompt has left over details like \"light hitting her jacket\" that you forget to remove I would like to add that some of the things this LoRA helps with, could probably be fixed with prompts. But personally i use Sonnet, or GPT 5.6 to prompt for me, and i almost never read the prompt. And from time to time they intentionally word the prompt very \"politicaly correct\", that may reduce the intended NSFW level of the image. And i find it simpler to just have this LoRA on standby to adjust on the fly when i find a prompt i like, without having to read the whole prompt and begin to rewrite parts of it.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:45:58.675321"
+}
@@ -0,0 +1,16 @@
+{
+  "hash": "027bb7dd5fd0a0c847797a71949b0a96823e826a58f00a04b7cc881b89c1fa1a",
+  "name": "PhotoBOX_ZIT",
+  "trained_words": [
+    "concept",
+    "lighting",
+    "photo",
+    "shadow",
+    "photography",
+    "control",
+    "exposure"
+  ],
+  "description": "This series aims to enhance the control capabilities of ZIT-T2I, it will be updated continuously. If you are looking for a controllable T2I method, this is definitely worth a try. Now, please like, follow, and share, so that when this series is updated, the system will automatically notify you. At the same time, it also has a Klein version, which can be obtained here. If you don't know how to use Slider-LORA, you can check this guide If you like my work, you can contact me through my X. If you are interested in how to train it, you can look here. | Angle-up &amp; down -10 &lt;&lt;&lt;&lt;&lt;&lt; LowAagle &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; HighAngle &gt;&gt;&gt;&gt;&gt;&gt; +10 Standard Sponsored | Race -5 &lt;&lt;&lt;&lt;&lt;&lt; More European &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; More Asian &gt;&gt;&gt;&gt;&gt;&gt; +5 Standard Sponsored | Body -5 &lt;&lt;&lt;&lt;&lt;&lt; Thin &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; Fat &gt;&gt;&gt;&gt;&gt;&gt; +5 Standard Sponsored | Aperture -5 &lt;&lt;&lt;&lt;&lt;&lt; small aperture &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; large aperture &gt;&gt;&gt;&gt;&gt;&gt; +5 Standard Sponsored | LOWquality &amp; HIGHquality -5 &lt;&lt;&lt;&lt;&lt;&lt; LOW quality &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; HIGH quality &gt;&gt;&gt;&gt;&gt;&gt; +5 Standard Sponsored | Age This LORA cannot be shared here; please check my private channel -5 &lt;&lt;&lt;&lt;&lt;&lt; Younger &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; Older &gt;&gt;&gt;&gt;&gt;&gt; +5 | ZoomOUT &amp; ZoomIN -5 &lt;&lt;&lt;&lt;&lt;&lt; ZoomOUT &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; ZoomIN &gt;&gt;&gt;&gt;&gt;&gt; +5 Standard Sponsored | Warm &amp; Cool -5 &lt;&lt;&lt;&lt;&lt;&lt; more cool &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; more warm &gt;&gt;&gt;&gt;&gt;&gt; +5 Standard Sponsored | Dark &amp; Light -5 &lt;&lt;&lt;&lt;&lt;&lt; more dark &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; more light &gt;&gt;&gt;&gt;&gt;&gt; +5 Standard Sponsored More LORA reserved slot … To help friends who are interested in training Slider-LORA, I have summarized some of my own training experiences. Those who need them can check here. | 🙈🙉🙊OK, that's all In addition to the Sponsored version, I will also provide exclusive private models, workflows, and usage guides. If you are also interested in this, please join my private channel. Thank you for reading this far. English is not my native language. The above content was translated by artificial intelligence. Please forgive me if there are any inaccuracies. Finally, have fun! AI never sleeps! Peace!",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:40:46.455753"
+}
@@ -0,0 +1,8 @@
+{
+  "hash": "02ddc686ba752b2bd8d2fdd208cd840baed9670418dbde6e9c25281e42d24673",
+  "name": "2509 Material Transfer",
+  "trained_words": [],
+  "description": "",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:10:45.825486"
+}
@@ -0,0 +1,15 @@
+{
+  "hash": "030c0c0b1a8ba905f652556644a4de63cfead6297dd14a9f7d0d1aa9cec1e6d8",
+  "name": "Project Art Styles for ZIT",
+  "trained_words": [
+    "style",
+    "art style",
+    "artistic",
+    "lora",
+    "zit",
+    "project art"
+  ],
+  "description": "Project Art Styles for ZIT *If you found this model useful, please give it a like! Experimental LoRas for Z image Turbo checkpoints, with different artistic styles Recommended checkpoint: SWIFT! LoRas: Style Illustrarealism: - Recommended strength ( 0.95 ) nudity is allowed Style TWO : -You can use the keyword: vibrant colors -Recommended strength: ( 0.95 ) Style Pin-up-stration: - Recommended strength ( 0.95 ) nudity is allowed Style ONE: - Recommended strength ( 1.0 ) Information: My intention is to make a collection of various style LoRas, presumably artistic, and group them together here. . *If you found this model useful, please give it a like! and Enjoy!",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:47:51.703465"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0337599dcb25514cc89400c20a41fe9ff2f434d44790e98d59b8abd044b3c396",
+  "name": "YFG Rigs [Flux]",
+  "trained_words": [
+    "YFG-Rigs"
+  ],
+  "description": "YFG Rigs: High-Tech Heavy Vehicles YFG Rigs is a LoRA that transforms ordinary vehicles into bold, futuristic designs—be it big rigs, tractor trailers, buses, SUVs, or even trains. Expect massive wheels, striking silhouettes, and an overall high-impact look. The keyword “YFG-R1gs” was used during training, but you don’t need a specific trigger word to tap into its potential. Key Features Futuristic Vehicle Aesthetic Amplifies scale, wheel size, and bold exterior details on almost any vehicle. Perfect for sci-fi, cyberpunk, or forward-looking automotive concepts. Versatile Strength Range Works reliably between 0.25 and 1.25 . 0.8 is the sweet spot for robust, dramatic transformations, but you can go lower for subtle modifications or higher for ultra-futuristic results. Wheels &amp; Big Bold Elements Naturally adds hefty tires, reinforced chassis, and dramatic architectural lines—even to non-vehicle prompts. Suited for scenes involving epic road warriors, post-apocalyptic caravans, or futuristic freight fleets. Best With Future-Focused Prompts Incorporating terms like “futuristic,” “cyber,” “advanced,” or “next-gen” heightens its imaginative visuals. Great for concept art, movie-style storyboards, or purely creative experiments. Recommended Usage No Mandatory Trigger “YFG-R1gs” was used in every caption during training, but is not required in your prompt. Suggested Prompts &amp; Themes “A massive futuristic 18-wheeler cruising a neon-lit highway” “Colossal off-road SUV with advanced hover wheels” “Next-gen bullet train with sleek angles and metallic plating” LoRA Strength 0.25 – 0.4 : Subtle transformations, slight futuristic hint. 0.8 : Ideal balance for distinctly futuristic details. 1.0 – 1.25 : Go all-out with sci-fi trucks, extra-large wheels, and radical design elements. Tips &amp; Tricks Combining With Other LoRAs Pair with a cyberpunk or dystopian model for immersive, gritty cityscapes. Alternatively, blend with an environment or architectural LoRA to create consistent futuristic backdrops. Play With Lighting &amp; Atmosphere Terms like “glowing neon,” “dusty desert roads,” or “dimly lit cargo station” can further define your vehicle’s narrative context. Highlight Scale Emphasize large, imposing perspectives—like vantage points from below or behind—for dramatic effect and to showcase those massive wheels. Subtle Adjustments If the design overwhelms your subject, reduce LoRA strength or add negative prompts (e.g., “no excessive wheels,” “minimal body kits”) to steer results. YFG Rigs takes standard vehicles to the next level with futuristic flair and robust, high-impact details. Whether you’re designing the ultimate sci-fi hauler or a next-gen off-roader, this LoRA revs up your concepts with big wheels and bold style. Experiment with strength settings and descriptive prompts to find your perfect futuristic ride!",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:57:24.655865"
+}
@@ -0,0 +1,8 @@
+{
+  "hash": "033c44dfb8c93c50c2bb36cb4b98066371ca2408e2d8544296b8725e83be5a2c",
+  "name": "Sinfully Stylish",
+  "trained_words": [],
+  "description": "",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:50:56.223409"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0347a82ab4f57f9a4183e9c38f656e51d7e5258751275b7beef17fb170f1e141",
+  "name": "Semi Real  - 77oussam®",
+  "trained_words": [
+    "semi-real-77"
+  ],
+  "description": "Here is the description for your \"semi-real-77.\" LoRA, formatted exactly like your example: Trigger Word: semi-real-77 Trained on: Flux Truevision - 77® Description: The semi-real-77. LoRA creates expressive digital artworks, expertly blending sharp realism with a distinct stylized elegance. Ideal for vibrant portraits, unique character concepts, and dynamic illustrations, it captures lifelike detail with a compelling artistic edge. Key Features: 🔹 Blended Realism – Combines realistic detail with a stylized, artistic interpretation. 🔹 Enhanced Expression – Infuses subjects with heightened emotional depth and visual impact. 🔹 Versatile Stylization – Perfect for diverse characters and narrative-driven scenes. Recommended Use: Use with semi_real . Strength: 0.7-1.3. Pairs best with Flux Truevision - 77®",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:50:31.426278"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "03e850da18ada54339b6448552a385efe5fc57bac3ae676fce4ad0f2570585a7",
+  "name": "Digital Abyss [FLUX/zImage]",
+  "trained_words": [
+    "bo-abyss"
+  ],
+  "description": "It would be incredibly kind of you to post the first image directly to this LoRA. This helps support the creator directly. After that, feel free to upload any images as you wish. Thank you so much for your support! ♥ Overview: The \" Digital Abyss \" Flux LoRA specializes in generating abstract, glitch-inspired portraits and scenes. With the ability to craft characters and environments that seem to dissolve into digital fragments, this LoRA is designed for creating surreal, futuristic worlds with a distinct glitch aesthetic. It combines dark, digital elements with otherworldly compositions, perfect for projects that need a cybernetic, fragmented, or dystopian feel. Features: Glitch Art Aesthetic: Captures the signature glitch art style, blending fragmented visuals and digital distortion with human characters. High-Fidelity Detail: The model can produce hyper-detailed images of faces and environments that incorporate code-like patterns, red glowing eyes, and digital decay. Versatile Application: From futuristic portraits to dystopian digital worlds, the LoRA is suitable for concept art, illustrations, and designs that explore the boundary between humanity and digital collapse. Use Cases: Futuristic Character Design: Ideal for creating characters with cybernetic features or visual effects that blend human and digital aesthetics. Glitch-Inspired Portraits: Perfect for generating abstract, fragmented portraits where the character merges with digital patterns and glitch effects. Surreal Dystopian Art: Useful for creating eerie, futuristic scenes that emphasize technology, glitch decay, and a sense of digital dissolution. Examples: \"Glitch Portraits\": A hyperrealistic portrait of a character with glowing red eyes, their face gradually dissolving into digital fragments. The character has long, flowing dark hair that moves as though caught in a digital breeze. Surrounding the face are glitch patterns—code-like lines and red highlights—intersecting with the skin, giving the appearance of the character being part human, part digital entity. The lighting is cold and minimal, with the glow from the eyes casting a faint red hue on the glitching parts of the face. The background fades into a dark, fragmented digital space, creating a surreal and eerie mood. \"Cybernetic Queen\": Create a stunning, regal cybernetic queen with a futuristic headpiece. Her face is adorned with a detailed mask resembling an owl, with large glowing yellow eyes and dark feathers framing her head, blending seamlessly with digital elements. The headpiece features intricate glitch patterns that subtly distort as if merging with the digital void. Her outfit combines metallic and organic textures, giving her a powerful and commanding presence. The lighting focuses on her face and chest, with a dark, glitchy background fading into abstract code, while red and gold accents highlight her otherworldly status. \"Dystopian Digital Realms\": A wide-angle view of a dystopian city, where broken, tech-infused landscapes stretch into the distance. The skyline is dominated by tall, crumbling towers, their neon signs flickering and glitching. In the foreground, characters in torn cybernetic armor wander through the debris, illuminated by the cold, digital glow of malfunctioning streetlights. The atmosphere is heavy with fog and digital distortion, with the sky filled with fragmented clouds of data. The overall mood is dark and ominous, with a palette of muted grays, blues, and occasional bursts of neon red, giving the scene a foreboding and decayed feeling. Usage Tips: To get the most out of this LoRA, use trigger words like \"bo-abyss\" , \" abstract digital elements \" and descriptive elements such as \"glitch art,\" \"digital distortion,\" \"fragmented texts\" \"glowing eyes,\" and \"metallic textures.\" Experiment with different combinations of these terms to create a variety of digital glitch effects. If you enjoy my work, feel free to support me here: https://ko-fi.com/bo4rsworld ♥ Thank you very much, my friend! ♥ I'm very excited to see the stunning and surreal creations you bring to life with this model!",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:29:23.493099"
+}
@@ -0,0 +1,14 @@
+{
+  "hash": "040632c4a820efe881fc5bcd26f1be9db12c91273a69953e232b1f3e84f072d0",
+  "name": "Klein Glow Slider",
+  "trained_words": [
+    "dark",
+    "concept",
+    "lighting",
+    "glow",
+    "slider"
+  ],
+  "description": "A glow / dark slider intended to be used with an already well defined scene where the glowing and dark setting is described appropriately. This helps tuning precisely how much the glow effect illuminates the scene. This works surprisingly well with Klein, with high scene consistency between generation. The sample images LoRA weights range from 0 to 3.0 (more glow). Hope you like it!",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:38:59.996401"
+}
@@ -0,0 +1,13 @@
+{
+  "hash": "040f92ba74dff4a7beb456d60cfced05cd215c9580931f5cf3fd1f744a0a1210",
+  "name": "Metal Art - CE",
+  "trained_words": [
+    "art",
+    "metal",
+    "style",
+    "filigree"
+  ],
+  "description": "Metal art, elaborate and intricate.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:44:07.216992"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "048c23ae326bfb376fc21cadd731cc4a82671e0a028a2c77fe2ac12f347803d9",
+  "name": "Velvet's Mythic Fantasy Styles | Flux + Pony + illustrious + ZiT + Anima + Krea2",
+  "trained_words": [
+    "An1meL1nes"
+  ],
+  "description": "Update Flux Version The new version has been trained to work on Flux models. From my testing Flux is amazing with sentence like prompts, and turns booru prompts to anime pics that don't have a lot of details but this LoRA fixes that: I tested it on SD Forge using the NF4 model and it work fine, you just need to change the Diffusion in Low Bits from Automatic to Automatic (fp16 LoRA) like this: The rest of the LoRAs are designed to work with Pony Diffusion XL , or any other Pony model. How to use 1- Manga Style (Blood Moon): Made from high quality monochrome images to give you a manga feel, oh and I called it blood moon because if you have something red in your prompt you might get a cool effect xD. Trigger words: This LoRA is without Trigger Words, but having \"monochrome, greyscale\" in your prompt can greatly enhance the results. Works on: 0.6-1 weights 2- Anime Illustrations Style: Made from very colorful and high quality data to improve your images and give them a badass feel. Trigger words: MythAn1m3 Works on: 0.6-1 weights. 3- Portrait Style: This style is made to create high quality portraits of fantasy characters, and most of the training data is made with semi realistic art style. Trigger words: MythP0rt Works on: 0.6-1 weights. 4- Flux: This style is made to create high quality fantasy art, and it has training data similar to the Portrait Style Trigger words: MythP0rt Works on: 0.5-1.5 weights, feel free to experiment but I recommend you to put the weight at 1. Other styles coming soon. If you have any problem try copying generation data from my examples, or send me a DM I can't wait to see what other people make with this :)",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:54:44.672787"
+}
@@ -0,0 +1,11 @@
+{
+  "hash": "04b8871d3f419c14b12e8f5842424645ead3406d3133128ed7d38d6a9944ab98",
+  "name": "Clusterfuck (western illustration/comic style)",
+  "trained_words": [
+    "Digital drawing",
+    "Digital illustration"
+  ],
+  "description": "First of all, I don't know what I'm doing really. I just trial and errored my way through dozens of variations of so many models I can't recall at this point. So best not to use it in anything commercial I guess I wanted western looking but not fully comic style look. Its like 90% there where I want it, but now matter what I tried I can't push it further. I can't get rid of the anime eyes on women and can't make the lineart more prominent - it would be perfect then. And hey, if you decide to give this a thumbs up or even review it, that is awesome. That stuff helps the most",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:26:02.902125"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "04c3e5af8314fccd00900aadb716dc01a109453e190d8c7683d42bc71c03b9e5",
+  "name": "NippleDiffusion - Flux1.Dev",
+  "trained_words": [
+    "nipples"
+  ],
+  "description": "I was tired of other LoRAs without the areolas textures and details. Most of the nipples I got until now using Flux was some soulless plain areolas without the depth it requires. Then I curated a mid-size dataset with the best breasts and areolas I could find today in the internet. I'm also releasing individual LoRAs for some of the trigger words listed below: Included in Genral Lora and also Stand-Alone files: big areolas - Rounded medium to big areola size dark nipples - Dark nipples with more contrast to the natural skin ghost nipples - Pale nipples that appears slightly long nipples - Nipples that you can bite easily puffy nipples - Small breasts with the tip of them covered with a dense nipple saggy breasts - breasts hanging a bit due to the gravity small areolas - Areolas with a small radius veiny areolas - Veins appearing under the skin Stand-Alone file only: banana tits - Similar to puffy, but focused on breast shape instead of nipples only silicone tits - The spheres from the 90s. It focuses on shape, you can combine other nipples empty tits - Similar to saggy, but empty flat tits - Flat chested woman oval areolas - When it's cold, the areola shape may change to oval. Good texture bumpy areolas - When it's cold, the areola texture becomes bumpy. Good texture wrinkled areolas - When it's cold big areolas becomes wrinkled! Good texture You can combine more than one. Inpainting them to improve the result is a good option. Use a strenght from 0.7 to 1.5 , depending on your scenario. Negative weight put clothes LOL Note below for the General LoRA only: This one tries to include all datasets from the other individual LoRAs. Trigger words (not really required at all) above \" may \" have some effect when inpainting and guided. If they don't work no problem, it's just Flux trying to use the best nipple to fit the girl. This is why there are individual LoRAs for each type. Additional trigger words only present in the General LoRA: ginger nipples - Nipples from the Redheads regular nipples - Normal regular nipples and areolas. In doubt? start here! Bonus that I added in case the full body appears, to have something right down there: hairy pussy - hairy pussy of a woman standing shaved pussy - shaved pussy of a woman standing Flux does what it wants LOL. I trained different concepts, but flux does not follow them as it did with SDXL. Flux seems doing a breast based on the overall girl appearance , but it's possible to achieve using inpainting and some prompt engineering. **Some few times it generates an almost translucent horizontal pattern in the image, and I don't know why",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:45:49.507132"
+}
@@ -0,0 +1,11 @@
+{
+  "hash": "05adff95c4992421b69b3e0b703619ebb3d49e7254b8b81d63b789daf53c0490",
+  "name": "Ivan Bilibin - CE",
+  "trained_words": [
+    "blbnCE_style",
+    "A traditional color line drawing."
+  ],
+  "description": "Art LoRA in the style of Ivan Bilibin.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:38:24.977967"
+}
@@ -0,0 +1,13 @@
+{
+  "hash": "05efdae9e472e06d168e122f5ebb890e7ef348cc047cf9876da6504c36d7d0e2",
+  "name": "LTX2 - IC LORA DETAILER",
+  "trained_words": [
+    "base model",
+    "lora",
+    "detailer",
+    "ltx2"
+  ],
+  "description": "✨ LTX-2 Detail Enhancement LoRA ltx-2-19b-ic-lora-detailer This LoRA is designed to enhance fine visual details and local clarity in LTX-2 generated videos, improving textures, edges, and small visual elements without altering the overall composition or motion . What it does: Increases perceived sharpness and micro-detail Enhances textures (faces, clothing, surfaces, environments) Improves visual readability in complex scenes Preserves motion and temporal consistency Best for: Close-ups and character shots High-resolution renders Cinematic scenes where detail matters Final polish before upscaling or export Creator tip: Use this LoRA with moderate weight to avoid over-sharpening. It works especially well before spatial upscaling for cleaner high-resolution results. 🧠 Usage Notes Designed for LTX-2 19B models Fully compatible with ComfyUI workflows Can be combined with camera control LoRAs Recommended to apply only one detail enhancement LoRA at a time From the original LTX Repo : https://huggingface.co/Lightricks",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:41:09.453652"
+}
@@ -0,0 +1,11 @@
+{
+  "hash": "06b87c2c7d5a42edf76af64e646145a88efd611c262f41220fbbed9a96dc5e97",
+  "name": "Light Slider - Krea2",
+  "trained_words": [
+    "tool",
+    "loraholic"
+  ],
+  "description": "Light Slider, sort of. This is a Light Slider that prioritize the darkest parts of the scene while the focus areas stay lit to some degree. If you want a more neutral effect you should use my Brightness Slider instead. There is a sample showing the difference beteween these slider in the Brightness Slider samples. Light LoRAs will almost always degrade quality , at least a little. So its best to use prompting as the main light controller, and use loras to push a little extra. Or use dedicated brightness and contrast nodes instead of a LoRA. The sample images was made with a 2-step workflow where the LoRAs only was used on the first pass, and i would recommend the same to keep the image quality high. Check out my prompting guide to master zoom/perspective: Controlling \"Zoom\" With Words Alone Recommended range: -5.0 to 8.0",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:40:08.212743"
+}
@@ -0,0 +1,13 @@
+{
+  "hash": "06b9dce5969f4dacd39c957c66bc0b80b0811186804e98567a9823022fae56ad",
+  "name": "Decay",
+  "trained_words": [
+    "aging",
+    "decay",
+    "style",
+    "decrepitude"
+  ],
+  "description": "DECAY *If you found this model useful, please give it a like! Experimental LoRa for Z image Turbo, for decay effect, aging , decrepitude ... How to use: - Add the LoRa to your workflow; recommended very high strength ( 2.0 to 6.0 ) And that's all! Information: In the example images you have the image without LoRa and then with LoRa with the indicated strength. With low strength, the Lora can serve as a gentle detailer. It hasn't been tested with negative strength, who knows what it will do! :P Experiment with it! Recommended checkpoint: SWIFT! . Enjoy!",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:28:30.023141"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "07ab35ce7229a54a7b89414eaea41009a764fac37836d6af0c52589761757374",
+  "name": "Comics Factory | Tome 2",
+  "trained_words": [
+    "Bradhamel art style"
+  ],
+  "description": "NOTE :Base model : Z Image Turbo &amp; Flux1 . Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:26:56.621323"
+}
@@ -0,0 +1,11 @@
+{
+  "hash": "07ec5445c0cbf0018aed2612642bfeeafacca89e790d283b73acb17cae52ad9a",
+  "name": "ta86_mirage_split_ZIT",
+  "trained_words": [
+    "mirage split",
+    "double exposure"
+  ],
+  "description": "Mirage_Split: (ongoing project) This LoRA transforms any subject into a fusion of form and vision. A striking double exposure effect refracted through the shimmering distortion of a desert mirage. Shapes remain clear and defined, yet within them lives a second world: landscapes, light patterns, textures, or scenes that bend, ripple, and flow across the contours of the subject. A exact double exposure wasn't the target, but a blend. When you go with simple backgrounds a clea double expose should be possible. Every figure, animal, object, or structure becomes a living silhouette for another image, with the overlay warped by subtle waves, heat shimmer, or refractive distortion. The result is a surreal, cinematic depth where two realities exist at once. The primary subject and the layered inner vision. Overlays can be crisp and vivid or softly diffused, but always framed by the edges of the base form. Inspired by the optical beauty of heat haze, refraction, and photographic double exposures, Mirage_Split excels at creating images where the overlay is not simply pasted on top, but appears to inhabit the very material of the subject. Light, color, and pattern flow along curves and folds, shifting naturally with perspective. It thrives in compositions with strong silhouettes, clear subjects, and overlays rich in structure or motion. Perfect for dramatic portraits, stylized animals, bold objects, and conceptual landscapes, this style captures the hypnotic rhythm of a mirage. Bending reality without losing clarity. The interplay between outer form and inner image produces results that are both dreamlike and sharply composed. And play with each other. Use it to create: – Portraits where faces or bodies contain layered landscapes, skies, or textures – Animals with vivid inner worlds: forests, oceans, or glowing light patterns within their forms – Objects and architecture refracting alternate scenes or intricate designs – Clothing and fabrics that reveal moving overlays like water, fire, or drifting leaves – Conceptual or symbolic imagery blending two realities into one silhouette Recommended Keywords: mirage split, double exposure, refracted double vision, liquid shimmer, layered overlay, silhouette world, internal landscape, heatwave blur, flowing texture, optical mirage, scene within scene mirage, double exposure, overlay → Use one to suppress the others when needed Parameter Guidance: Use 0.4–0.6 for subtle shimmer and soft refractive layering. Slight double exposure Use 0.7–0.8 for a creative overlay. Be careful. Sometimes doing a bit too much :D",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:29:42.274847"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "07ef0fac7ff5cbaec299edf1a6c9ad9cb2c5a1bcb53552bddfc0d8fb3b4b40a8",
+  "name": "KreaShizuka",
+  "trained_words": [
+    "Bradhamel art style"
+  ],
+  "description": "NOTE : Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:40:01.283069"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0828887072c8d6d94526a09b9a21d014aa15aefadf6e294a58be6801b23ae1bc",
+  "name": "Borderlands Style",
+  "trained_words": [
+    "yubord"
+  ],
+  "description": "ZiT Version 1.0 : Recommanded weight: 0.7 - 1.2 Optional trigger word: yubord (sometimes helpful on very difficults subjects) if you use trigger word , 0.7 is a good start! ======= V2: ======= FR: Mise à jour significative comparé à la v1, les décors sont bien mieux pris en charge. Paramètres recommandés: poid de 0.6 à 1.2 D'après mes tests, entre 0.6 et 0.8 suffisent la majorité du temps pour des rendus avec des personnages, et de 0.8 a 1.1 pour des rendus types architectures. N'hésitez pas à tester avec différents modèles également. N'hésitez pas à tester par vous-même, et à poster vos créations sur la page ! :) ENG: Significantly updated compared to v1, backgrounds are much better supported. Recommended parameters: weight from 0.6 to 1.2 According to my tests, between 0.6 and 0.8 is sufficient most of the time for character renders, and 0.8 to 1.1 for architectural renders. Feel free to test with different models too. Feel free to test for yourself, and post your creations on the page! :) ======= V1: ======== F R : Voici mon premier Lora, basé sur les jeux Borderlands. Paramètres recommandés: euler simple , cfg 3.5 , poids 1-1.5 selon les prompts. Mot-clé important: cel shading Vous pouvez aussi essayer en complétant avec illustration, drawing, etc... :) === Il n'est pas parfait, mais il est cependant assez flexible. Merci beaucoup à mes amis @taek75799 , @Fadoo2077 et @NGone pour m'avoir aidé. Allez voir leurs créations pour les soutenir :) N'hésitez pas à poster vos créations avec mon lora, et si vous souhaitez me soutenir les buzzs sont les bienvenus notamment pour une v2 :) ENG: Here's my first Lora, based on the Borderlands games. Recommended settings: single euler , cfg 3.5 , weight 1-1.5 depending on prompts. Important keyword: cel shading You can also try supplementing with illustration, drawing, etc... :) === It's not perfect, but it's pretty flexible. Many thanks to my friends @taek75799 , @Fadoo2077 and @NGone for helping me. Check out their creations for support :) Feel free to post your creations with my lora, and if you want to support me buzzs are welcome especially for a v2 :)",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:24:28.033169"
+}
@@ -0,0 +1,13 @@
+{
+  "hash": "083ecbd1438396452285838523594c4500868f6cae3043b7c85e3fc464846cb6",
+  "name": "Klein Detail Slider",
+  "trained_words": [
+    "concept",
+    "detail",
+    "slider",
+    "detailing"
+  ],
+  "description": "A simple detail LoRA slider that increases the details in an image. Works very well in I2I to increase the details of a blurred or low resolution photo. See the sample with the woman, left is a T2I 256x256 image, right is a 1024x1024 I2I generated with this LoRA, no prompt. The samples weights range from -10 to 10 but it can easily be pushed past that. Hope you like it.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:38:59.521861"
+}
@@ -0,0 +1,13 @@
+{
+  "hash": "0853ba8d35805d4f921f56887f41e3a479c4c5446ff6ab73f8bccda75af2e37f",
+  "name": "Dark Atmospheric Style - CE",
+  "trained_words": [
+    "dark",
+    "shadow",
+    "style",
+    "atmospheric"
+  ],
+  "description": "The Dark Atmospheric LoRA was trained to produce a style characterized by shadow and mist with a slightly diffuse effect.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:27:58.732054"
+}
@@ -0,0 +1,11 @@
+{
+  "hash": "086578e2833610a52127851d75e8dfc03d2b9682b4fb5a0e59fd3ee111b517ca",
+  "name": "Desimulate Style [Z Image Turbo] LoRA",
+  "trained_words": [
+    "Desimulate",
+    "Modern Hi-Bit Pixel Art"
+  ],
+  "description": "Desimulate Style [Z Image Turbo] LoRA Early access on Patreon (support): https://www.patreon.com/mm744",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:28:47.059719"
+}
@@ -0,0 +1,16 @@
+{
+  "hash": "08b5971337ed3539a7714293416a9dd5720d9341b01b05da0ba02f54c6051541",
+  "name": "PhotoBOX_ZIT",
+  "trained_words": [
+    "concept",
+    "lighting",
+    "photo",
+    "shadow",
+    "photography",
+    "control",
+    "exposure"
+  ],
+  "description": "This series aims to enhance the control capabilities of ZIT-T2I, it will be updated continuously. If you are looking for a controllable T2I method, this is definitely worth a try. Now, please like, follow, and share, so that when this series is updated, the system will automatically notify you. At the same time, it also has a Klein version, which can be obtained here. If you don't know how to use Slider-LORA, you can check this guide If you like my work, you can contact me through my X. If you are interested in how to train it, you can look here. | Angle-up &amp; down -10 &lt;&lt;&lt;&lt;&lt;&lt; LowAagle &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; HighAngle &gt;&gt;&gt;&gt;&gt;&gt; +10 Standard Sponsored | Race -5 &lt;&lt;&lt;&lt;&lt;&lt; More European &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; More Asian &gt;&gt;&gt;&gt;&gt;&gt; +5 Standard Sponsored | Body -5 &lt;&lt;&lt;&lt;&lt;&lt; Thin &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; Fat &gt;&gt;&gt;&gt;&gt;&gt; +5 Standard Sponsored | Aperture -5 &lt;&lt;&lt;&lt;&lt;&lt; small aperture &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; large aperture &gt;&gt;&gt;&gt;&gt;&gt; +5 Standard Sponsored | LOWquality &amp; HIGHquality -5 &lt;&lt;&lt;&lt;&lt;&lt; LOW quality &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; HIGH quality &gt;&gt;&gt;&gt;&gt;&gt; +5 Standard Sponsored | Age This LORA cannot be shared here; please check my private channel -5 &lt;&lt;&lt;&lt;&lt;&lt; Younger &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; Older &gt;&gt;&gt;&gt;&gt;&gt; +5 | ZoomOUT &amp; ZoomIN -5 &lt;&lt;&lt;&lt;&lt;&lt; ZoomOUT &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; ZoomIN &gt;&gt;&gt;&gt;&gt;&gt; +5 Standard Sponsored | Warm &amp; Cool -5 &lt;&lt;&lt;&lt;&lt;&lt; more cool &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; more warm &gt;&gt;&gt;&gt;&gt;&gt; +5 Standard Sponsored | Dark &amp; Light -5 &lt;&lt;&lt;&lt;&lt;&lt; more dark &lt;&lt;&lt;&lt;&lt;&lt; 0 &gt;&gt;&gt;&gt;&gt;&gt; more light &gt;&gt;&gt;&gt;&gt;&gt; +5 Standard Sponsored More LORA reserved slot … To help friends who are interested in training Slider-LORA, I have summarized some of my own training experiences. Those who need them can check here. | 🙈🙉🙊OK, that's all In addition to the Sponsored version, I will also provide exclusive private models, workflows, and usage guides. If you are also interested in this, please join my private channel. Thank you for reading this far. English is not my native language. The above content was translated by artificial intelligence. Please forgive me if there are any inaccuracies. Finally, have fun! AI never sleeps! Peace!",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:48:05.258503"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "08b7ce0824cd6051506c913628b2199ff56f03e4cddd302604e4cf0fe87bf42e",
+  "name": "YFG Zaat [Flux | Krea]",
+  "trained_words": [
+    "YFG-Zaat style"
+  ],
+  "description": "Zaat: Futuristic Robotic Vehicle Design Introducing Zaat , a LoRA tailor-made for showcasing futuristic space vehicles, cutting-edge machines, and ultra-modern robots and robotic structures. This concept features a primarily white color palette—evoking the sleek allure of polished plastic or high-grade alloys—while highlighting the gleaming sophistication of next-gen technology. Key Attributes Futuristic White Aesthetic Zaat infuses your renders with the look of shiny white surfaces, reminiscent of futuristic composite materials or painted alloys. Robotic Structures and Vehicles Whether you're depicting advanced spacecraft, colony rovers, hovering drones, or android frames, this LoRA ensures mechanical features shine with a clean, futuristic appeal. Seamless Integration Zaat is designed to work harmoniously with other styles and is especially well-suited for sci-fi, space exploration, or cybernetic-themed compositions. Recommended Usage Trigger / Prompt: Use keywords like “YFG-Zaat” , “futuristic machine” , “shiny white alloy,” \"robot'\" or “high-tech plastic” to emphasize the distinctive aesthetic. Combine with your usual subject prompts, e.g., “futuristic cityscapes,” “space exploration crew,” or “robotic vehicle designs.” LoRA Strength (Weight): Recommended to start between 0.7 - 1.2 . Works great at 1.0. Adjust depending on how dominant you want the style to be in your final image. Complementary Prompts &amp; Themes: “Ethereal lighting,” “sterile environment,” “clean lines,” “geometric precision,” etc. Perfectly suits science-fiction worlds, near-future concept art, and advanced aerospace design. Tips &amp; Tricks Experiment With Environment Try pairing Zaat with luminous backgrounds, minimalist interiors, or epic cosmic vistas to create a crisp, high-tech atmosphere. Add Subtle Accents Experiment with complementing colors—like neon blues, subtle grays, or brushed metals—to break up the white palette while retaining the sleek design. Composition &amp; Lighting Dramatic or “studio-style” lighting often emphasizes Zaat’s reflection details, amplifying the glossy surfaces of the white material. Usage Disclaimer This LoRA was trained to emphasize clean shapes, smooth reflective surfaces, and an overall futuristic vibe. Adjust prompts, negative prompts, and LoRA strength to best match your artistic vision. Please abide by the licensing terms associated with this model and ensure that your usage of Zaat aligns with the respective rules and guidelines. Zaat injects a visionary twist into sci-fi or conceptual designs, elevating them with a pristine white aesthetic and robotic sophistication. Enjoy crafting ultra-modern, awe-inspiring scenes with this cutting-edge LoRA!",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:57:30.506496"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "099fc4b27e1f03398fcd3bb9e3b6a73ed6aeb89a7abe6a09f80974546269e99b",
+  "name": "Daniel Hahn",
+  "trained_words": [
+    "Daniel Hahn art"
+  ],
+  "description": "Daniel Hahn , also known as Daytoner, is a concept artist based in Los Angeles. He specializes in creating futuristic designs, particularly robots and human-machine hybrids. His work combines elements of car design and character development, resulting in intricate and dynamic creations. Hahn employs a variety of techniques, including 3D modeling, digital painting, and photobashing, using tools like ZBrush, Photoshop, and Substance Painter. His art is influenced by urban fashion, Japanese aesthetics, and the world of art toys, making his style both unique and captivating NOTE : Base model : Z Image Turbo &amp; Flux1 . Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow. IMPORTANT NOTE : This model is a tribute to the artist and not an attempt to copy or reproduce his works. VERY IMPORTANT NOTE : Do not like my models, do not give me buzz, do not follow me, otherwise you will be reported to Civitai for attempted corruption",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:27:46.715978"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "09b1b45ceed0202929bca528e51b50208d0160f4e9d2ba0f42cb7e739a43577f",
+  "name": "Pixel Art Style Lora",
+  "trained_words": [
+    "Pixel Art style."
+  ],
+  "description": "Pixel art style lora. Works well with strength between .6-1. Useful prompts: Scene, portrait, sprite. If you lower the strength of the lora then it generally increases the resolution of the pixel art (especially if you are using other lora's in combination with this one)",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:47:36.710709"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "09cbd7597218f326e4f86b2637627ae1db229042e045c8c8cf761ab3b78acbeb",
+  "name": "Space Worlds : Poetic 5 - Preview 1 - ZIT",
+  "trained_words": [
+    "z1os"
+  ],
+  "description": "Finding all my models or profile elsewhere than Civitai is without my consent ! Please don't repost my files. Send people to my Civitai profile, thanks :) -- This version was made from a new dataset I made. These are just previews. JUST FOR FUN AND TESTING ;) About preview 3 : originaly made for Z Image Base but the training failed so I went back to ZIT ;) Oh another preview ? Yes preview 4 + Poetic V5 minis = just for fun :) -- Space Worlds Poetic V5 Preview : The Witness Were you there when it all started ? I saw it... the rush to oversized structures... The great expanse in space, ships and now capital ships. As one would disapear, a nation near extinction. Why this nonsense ? -- Follow me, I'm the witness I have no home I'm a walker, I travel with my teleporter, never stop. Follow me, explore these worlds, we'll meet friends somewhere... -- All versions : HOW TO USE : Strength : 1 tested Steps : 15 - 20 tested Checkpoints : Any but I mostly used the Base Fp8 and Base BF16 models. Adetailer : not used, your choice Sampler : Tested with EULER and DPM ++ 3M SDE Scheduler : NORMAL or SIMPLE or BETA -- Trigger word : z1os -- Some Effects are built in. -- Have fun ^^",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:51:55.687969"
+}
@@ -0,0 +1,18 @@
+{
+  "hash": "0a04c97fa74aecc231ec3b6ff97291a584a975a41a2de999f837fe5f05a26e8a",
+  "name": "Surreal Epic",
+  "trained_words": [
+    "concept",
+    "art",
+    "epic",
+    "fantasy",
+    "sci fi",
+    "landscape",
+    "surreal",
+    "hyper-realistic",
+    "dream-logic"
+  ],
+  "description": "A cinematic LoRA that fuses hyper-realistic photography with dream-logic surrealism. Impossible alien megastructures, blood-red rivers under biomechanical tripods, medieval knights facing UFOs, glowing equations floating in twilight skies, and god-ray volcanoes mirrored in obsidian lakes and more. Use your imagination. Best strength: 0.3-0.6: subtle mood + epic lighting + surreal color grading, works as refiner for base model 0.7-1: full invasion of the impossible (floating monoliths, biomechanical skies, alien geometry, anachronistic tech etc) I recommend this clip: Quants here: https://huggingface.co/mradermacher/Josiefied-Qwen3-4B-abliterated-v2-GGUF/tree/main",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:53:28.988231"
+}
@@ -0,0 +1,17 @@
+{
+  "hash": "0a0ae90d347a5ea844b7af67d586349ca672316c2d7674ead68206b1a1fd273e",
+  "name": "Flux hyperkraximalism | breaking boundaries",
+  "trained_words": [
+    "concept",
+    "surrealism",
+    "masterpiece",
+    "enhancer",
+    "detailer",
+    "maximalism",
+    "special",
+    "flux1.d"
+  ],
+  "description": "Flowing Elements Vivid Colors Surreal Aesthetic Chaotic Versatility Fantastic Enhancement Unpredictable Creativity Mind-blowing results Pour out your creativity and let hyperkraximalism amaze you! hyperkraximalism version comparison | Civitai",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:36:01.269257"
+}
@@ -0,0 +1,15 @@
+{
+  "hash": "0a267902be7a0d77656129fa3ca02ef6130c9a62af6cffd89b9c99544fb8af56",
+  "name": "Flux.1 Turbo Detailer",
+  "trained_words": [
+    "photorealistic",
+    "hyperrealism",
+    "style",
+    "lora",
+    "detailer",
+    "flux.1"
+  ],
+  "description": "Post Your First Image in the Model Gallery Directly! This is the best way to support creators. 🎨✨ LoRa for Amazing Details Elevate Your Outputs with High-Speed, Optimized LoRa Unlock stunning detail and realism in just seconds. This highly optimized LoRa transforms your outputs with intricate character, object, and environment enhancements. Key Features: ✨ Exceptional Detail: Amplify every aspect of your prompts with rich, nuanced detailing. 💡 Realistic Lighting &amp; Visuals: Achieve lifelike visuals with dynamic, true-to-life lighting. 🎯 Precision in Features: Perfectly handles fine details, ensuring accuracy in areas like eyes, hands, and facial expressions. 🎨 Versatile &amp; Powerful: Ideal for any subject or style, enhancing depth and quality across the board. Enjoy experimenting ! Tested with FLUX .1 Dev, Schnell checkpoints, and with mix of Turbo Alpha 8 steps. Recommended Settings 0.2 - 0.9 Thank you so much for using this Lora. Hope you get a lot of beautiful results ♥",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:53:59.376691"
+}
@@ -0,0 +1,8 @@
+{
+  "hash": "0a2f68b45d4eba11b47e6381bf44446d561e70510cbdd6454365304c0881aa3b",
+  "name": "Detail Slider - (Krea 2) - Loraholic",
+  "trained_words": [],
+  "description": "",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:28:47.239685"
+}
@@ -0,0 +1,13 @@
+{
+  "hash": "0aae532bbe5c166d359585dfec983199d8c35158ccfe6ada43594d6ba059ee80",
+  "name": "Flux Kontext Zoom Out LoRA",
+  "trained_words": [
+    "Zoom out and keep the visible subject exactly the same in position",
+    "scale and appearance. Expand the canvas evenly in every direction and fill all new areas with a natural continuation of the scene",
+    "matching the original lighting",
+    "perspective and photographic style."
+  ],
+  "description": "After dozens of experiments I’ve settled on the version that’s giving me the most reliable zoom‑outs. I tried training separate LoRAs for extreme , large , and medium zoom levels, but those models were too unpredictable—so I’m sticking with this single “all‑rounder.” Known caveats Out‑paint artifacts – some images pick up chunky/pixelated edges in the newly generated areas. Human close‑ups – very tight crops of faces, hands, or bodies can warp badly. No precise zoom slider – you can’t tell it “zoom out 10×”; results vary, so experiment. How to prompt Use the base prompt below, then bolt on whatever you’d like to see in the expanded frame. Example: Zoom out and keep the visible subject exactly the same in position, scale and appearance. Expand the canvas evenly in every direction and fill all new areas with a natural continuation of the scene, matching the original lighting, perspective and photographic style. You can change the target latent image size different from your source image size. For example; if your image is vertical, you can expand/apply the zoom out horizontally. Feel free to check the example images. LoRA also works with Nunchaku workflows. That’s it—give it a spin and let me know how it works for you! LoRA trained with fal.ai Flux Kontext LoRA Trainer, with 70+ pairs, 0.0003 LR, 3000 steps",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:57:44.177662"
+}
@@ -0,0 +1,8 @@
+{
+  "hash": "0abae244ba78da90ca196b44f6de8e2a89ecb28f1d67815efc655bb4ea67131d",
+  "name": "2509 Image Edit Light Restoration v2",
+  "trained_words": [],
+  "description": "",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:10:35.986787"
+}
@@ -0,0 +1,11 @@
+{
+  "hash": "0afcc9d9db7cdc3cecdd577d12c4fcce240cf53553b8938d2c8db94087eb3bfc",
+  "name": "Watercolor Flux",
+  "trained_words": [
+    "kk_wcolor",
+    "watercolor painting"
+  ],
+  "description": "Turns you images into watercolor paintings with splotches, splatters and drippings Example prompt: a watercolor painting in kk_wcolor style of [rest of your prompt], white background with splotches, splatters and drips of paint.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:56:35.966024"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0afe486ead7976eaff26b4b283835dfbc45fac1932d9c5a404df81a82e4ce49b",
+  "name": "Watercolor painting",
+  "trained_words": [
+    "VarcoterolV7 art style"
+  ],
+  "description": "NOTE : Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:56:49.914029"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0b2f5f39bb3e416c765a242519b4b9e713a66ecd9b3b155c420ae7d003b202d2",
+  "name": "Red Light District",
+  "trained_words": [
+    "Bradhamel art style"
+  ],
+  "description": "NOTE : Base model category: ZImageTurbo &amp; Flux1 . Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:49:31.406781"
+}
@@ -0,0 +1,8 @@
+{
+  "hash": "0b45b318448bfdfebb83da6e700a44af895ba5f768974553f4d3e18360caacb8",
+  "name": "2509 Eigen Banana fp16",
+  "trained_words": [],
+  "description": "",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:10:21.637151"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0cd9ec0f3ee9d111af79bfbf1cecfd1d1a874e9df08c17c168998fa89107b1a5",
+  "name": "Velvet's Mythic Fantasy Styles | Flux + Pony + illustrious + ZiT + Anima + Krea2",
+  "trained_words": [
+    "mythp0rt"
+  ],
+  "description": "Update Flux Version The new version has been trained to work on Flux models. From my testing Flux is amazing with sentence like prompts, and turns booru prompts to anime pics that don't have a lot of details but this LoRA fixes that: I tested it on SD Forge using the NF4 model and it work fine, you just need to change the Diffusion in Low Bits from Automatic to Automatic (fp16 LoRA) like this: The rest of the LoRAs are designed to work with Pony Diffusion XL , or any other Pony model. How to use 1- Manga Style (Blood Moon): Made from high quality monochrome images to give you a manga feel, oh and I called it blood moon because if you have something red in your prompt you might get a cool effect xD. Trigger words: This LoRA is without Trigger Words, but having \"monochrome, greyscale\" in your prompt can greatly enhance the results. Works on: 0.6-1 weights 2- Anime Illustrations Style: Made from very colorful and high quality data to improve your images and give them a badass feel. Trigger words: MythAn1m3 Works on: 0.6-1 weights. 3- Portrait Style: This style is made to create high quality portraits of fantasy characters, and most of the training data is made with semi realistic art style. Trigger words: MythP0rt Works on: 0.6-1 weights. 4- Flux: This style is made to create high quality fantasy art, and it has training data similar to the Portrait Style Trigger words: MythP0rt Works on: 0.5-1.5 weights, feel free to experiment but I recommend you to put the weight at 1. Other styles coming soon. If you have any problem try copying generation data from my examples, or send me a DM I can't wait to see what other people make with this :)",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:54:43.204184"
+}
@@ -0,0 +1,18 @@
+{
+  "hash": "0d061b16de09997281ede379fe7b5910e99b36cfadd856184630327bdd815baf",
+  "name": "Anime art",
+  "trained_words": [
+    "comic book",
+    "anime",
+    "drawing",
+    "art",
+    "cyberpunk",
+    "niji",
+    "style",
+    "illustration",
+    "painting"
+  ],
+  "description": "NOTE :Base model : Z Image Turbo &amp; Flux1 . Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:22:45.998341"
+}
@@ -0,0 +1,11 @@
+{
+  "hash": "0d181d2d09a4e5f6da959acafa14dd138a2b0c3d0347ec6567caa4b850ff6c2b",
+  "name": "Apply Color Palette [Qwen & Klein]",
+  "trained_words": [
+    "Apply this palette to <object>",
+    "Apply this palette to the entire image"
+  ],
+  "description": "Modifies the first image to apply the color palette supplied in the second image. Prompting is capable of targeting specific elements of the image. To generally impose the color palette, use this prompt: Apply this palette to the entire image To only apply the palette to specific elements, use this prompt: Apply this palette to &lt;object&gt; Apply this palette to the their outfits and the trees. Apply this palette to the women's dresses The model is trained to generally avoid affecting the ambient light and skin tones, but if you wish to add a baseline color cast, changes the ambient light, use: Add a &lt;color&gt; hue Add a blue hue To remove a color cast from an image that already has one: Remove the &lt;color&gt; hue Remove the tan hue",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:10:07.980448"
+}
@@ -0,0 +1,14 @@
+{
+  "hash": "0d9bd1b873a7863e128b4672e3e245838858f71469a3cec58123c16c06f83bd7",
+  "name": "Detail Tweaker XL",
+  "trained_words": [
+    "concept",
+    "detailed",
+    "detail",
+    "enhancer",
+    "undetailed"
+  ],
+  "description": "Detail tweaker for SDXL. Works with weights [-3, 3] Use positive weight to increase details and negative weight to reduce details. Good weight depends on your prompt and number of sampling steps, I recommend starting at 1.5 and then adjusting it.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:16:20.488989"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0dabbc5210f2036785b763893817c2df4a9e4d6cff59127d1d1264b7026a7d94",
+  "name": "Fresh",
+  "trained_words": [
+    "Bradhamel art style"
+  ],
+  "description": "NOTE : Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:32:02.920792"
+}
@@ -0,0 +1,19 @@
+{
+  "hash": "0dd4acc600df64fd6a15212466014c75e6d5c4b642b0a45d2598817d57c44b23",
+  "name": "GPT  Image 1 Style [FLUX] (FLUX v0.1)",
+  "trained_words": [
+    "aidmagptimage",
+    "gpt image",
+    "gpt image 1",
+    "realistic",
+    "openai",
+    "concept",
+    "gpt",
+    "woman",
+    "anime",
+    "photo"
+  ],
+  "description": "v0.1 strength comparison",
+  "source": "civitai",
+  "imported_at": "2026-07-23T14:51:13.684390"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0e1587bb5aaa69748c6545dd997fc70dab52f9cf98ce608f08ab045946030909",
+  "name": "HXHY-RealisticKontextLoRA",
+  "trained_words": [
+    "Convert to a realistic art style"
+  ],
+  "description": "Change Log: Version 1.6: Fine-tuned the quality and effect of Kontext's realistic conversion, with better generalization than version 1.1. Trigger word: Convert to a realistic art style. Recommended value 1.0, if the conversion is not obvious, you can set the weight to 0.6. Version 1.1: Fine-tuned the quality of Kontext's realistic conversion. Trigger word: Convert to a realistic art style. Recommended value 1.0, if the conversion is not obvious, you can set the weight to 0.6. Besides the trigger word, remember to add more relevant descriptions, such as 1gril, otherwise the effect may not be good. General workflow: https://civitai.com/models/1733176/fluxkontextdev-lora-general-workflow Automatic size general workflow: https://civitai.com/models/1733187/fluxkontextdev-lora-general-workflow-auto-size-fluxkontextdev-lora",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:35:29.483514"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0e24f2d762e5c6b9e1dd19fd9e40c1acfe1edb740e458048dd76217c3eb1adb5",
+  "name": "Qwen-Edit_Anime2Real",
+  "trained_words": [
+    "将图片转为真实风格"
+  ],
+  "description": "Anime2Real is a Qwen-Edit Lora designed to convert anime characters into realistic styles. The current version is beta, with characters appearing somewhat greasy. The Lora strength must be set to &lt;1. You may click the link below to test the LoRa effect: Anime2Real V1.0 Update: This version makes characters appear less greasy and significantly more natural. The default generation produces Western facial features; to generate Asian or other facial types, simply load an additional Realistic Series LORA.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:23:01.150270"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0e3cc2a9857f706e95164e329693c73bcc9602909e1fddadf0436c8061d7d4c6",
+  "name": "Azat Nurgaleev",
+  "trained_words": [
+    "Azanurgale style"
+  ],
+  "description": "Azat Nurgaleev is a Russian digital artist and educator, best known as the founder of the Skills Up School and for his expressive portrait work. Artistic Profile Azat Nurgaleev specializes in digital painting , with a strong emphasis on portraiture, character design, and expressive lighting . His work often features dramatic chiaroscuro, painterly textures, and emotionally resonant poses. He shares tutorials and insights into his process on platforms like ArtStation , Patreon , and YouTube. Educator &amp; Founder He is the founder of Skills Up School , a well-regarded art education platform that offers courses in drawing, digital painting, and concept art. His teaching style blends classical fundamentals with modern digital techniques, making him a popular mentor among aspiring artists. Online Presence Azat regularly publishes video tutorials on portrait techniques, such as proportion, lighting, and expressive anatomy. His YouTube series breaks down facial features and gestures with clarity and humor, helping students move beyond basic shapes to nuanced renderings. NOTE : Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow.. IMPORTANT NOTE : This model is a tribute to the artist and not an attempt to copy or reproduce his works. Flux1.D is unable to reproduce a graphic universe on which it was trained, the goal is solely to expand Flux's pictorial capabilities.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:24:08.008104"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0e9f7d3ae26e4e6eab893c851e6d10e1bda7579ecfa878c4c40a21929b65896b",
+  "name": "Axel Sauerwald",
+  "trained_words": [
+    "Axaurwal style"
+  ],
+  "description": "Axel Sauerwald is a German concept artist and illustrator known for his work in fantasy and role-playing game universes. He began his career at Atomhawk Design Ltd in 2018 and transitioned to freelance work in 2020. Since then, he has collaborated with major studios such as Blizzard Activision, Wizards of the Coast, and Aaron Sims Creative. His illustrations have appeared in publications like Clarkesworld Magazine, 3DTotal, and Spectrum 27. Sauerwald is also active in the European tabletop RPG scene, contributing artwork to titles like The Dark Eye, Legend of the Five Rings, and Rokugan, often through publishers like Ulisses Spiele and Fantasy Flight Games. He is currently based in Trier, near the Moselle region of Germany. NOTE : Tips for better LoRA expression: Use latent injection instead of empty latent Favor short prompts Avoid using CN or limit its weighting Favor a checkpoint with fp16/fp8 precision (avoid Nunchaku) Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow. All licensing conditions for the Flux Dev model apply. You can find the details here . IMPORTANT NOTE : This model is a tribute to the artist and not an attempt to copy or reproduce his works. Flux1.D is unable to reproduce a graphic universe on which it was trained, the goal is solely to expand Flux's pictorial capabilities. VERY IMPORTANT NOTE : Do not like my models, do not give me buzz, do not follow me, otherwise you will be reported to Civitai for attempted corruption",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:24:07.702495"
+}
@@ -0,0 +1,17 @@
+{
+  "hash": "0eb5df85d5bc5fba32966de8b357c7643413219479605cc933412b60305c01f8",
+  "name": "Wan2.1_FusionX -The LoRa",
+  "trained_words": [
+    "style",
+    "phantom",
+    "wan",
+    "i2v",
+    "t2v",
+    "wan2.1",
+    "vace",
+    "fusionx"
+  ],
+  "description": "📢 7/1/2025 Update! New: FusionX Lightning Workflows Looking for faster video generations with WAN2.1? Check out the new FusionX_Lightning_Workflows — optimized with LightX LoRA to render videos in as little as 70 seconds (4 steps, 1024x576) ! 🧩 Available in: • Native • Native GGUF • Wrapper (VACE &amp; Phantom coming soon) 🎞️ Image-to-Video just got a major upgrade!!!!!! Better prompt adherence , more motion , and smoother dynamics. ⚖️ FusionX vs Lightning? Original = max realism. Lightning = speed + low VRAM, with similar quality using smart prompts. 👉 Check it out here ☕ Like what I do? Support me here: Buy Me A Coffee 💜 Every coffee helps fuel more free LoRAs &amp; workflows! 🚨✨ We finally cooked up FusionX LoRa's!! 🧠💥 This is huge – now you can plug FusionX into your favorite workflows as a LoRa on top of the Wan base models and SkyReels models!🔌💫 You can still stick with the base FusionX Model if you already use it, but if you would rather have more control over the \"FusionX\" strength and a speed boost, then this might be for you. ⚡ Speed Boost Example (RTX 5090): FusionX as a full base model: 8 steps = 160s ⏱️ FusionX as a LoRA on Wan 2.1 14B fp8 T2V : 8 steps = 120s 🚀 🧪 Bonus You can bump up the FusionX LoRA strength and lower your steps for even more of a speed boost while testing/drafting. Example: strength 2.00 with 3 steps = 72s Or lower the strength and increase your steps to get a less “FusionX” look. (Experiment with settings) ⚡🔍 This LoRa also works with SkyReels models. (Workflows for that coming soon) 🔧 What’s Included: T2V (Text to Video) 🎬 – works great with VACE ❄️ I2V (Image to Video) 🖼️➡️📽️ A dedicated Phantom LoRA 👻 Workflows for each can be found HERE and include all the default settings which have been used in the example video's posted. Settings have not changed, you still need to follow the same guidelines. Please see the workflows for best practices when it comes to settings, you can experiment at your own risk. 📝 Want better prompts? All my example video prompts were created using this custom GPT: 🎬 WAN Cinematic Video Prompt Generator Try asking it to add extra visual and cinematic details — it makes a noticeable difference. 💡 What’s Inside this loRa: 🧠 CausVid – Causal motion modeling for better scene flow and dramatic speed boot 🎞️ AccVideo – Improves temporal alignment and realism along with speed boot 🎨 MoviiGen1.1 – Brings cinematic smoothness and lighting (t2v only) 🧬 MPS Reward LoRA – Tuned for motion dynamics and detail ✨ Custom LoRAs (by me) – Focused on texture, clarity, and fine details. (These both were set to very low strengths and have a very small impact) ⚠️ Disclaimer: Videos generated using this model are intended for personal, educational, or experimental use only , unless you’ve completed your own legal due diligence. This model is a merge of multiple research-grade sources , and is not guaranteed to be free of copyrighted or proprietary data . You are solely responsible for any content you generate and how it is used. If you choose to use outputs commercially, you assume all legal liability for copyright infringement, misuse, or violation of third-party rights. When in doubt, consult a qualified legal advisor before monetizing or distributing any generated content.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:55:39.623374"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0ed84d6586ac445e2e21b992057ae9dd3a3dfd94466f5bbf960d033db79eb73f",
+  "name": "Visionary - CE",
+  "trained_words": [
+    "vsnryCE_style"
+  ],
+  "description": "This LoRA blends elements of romanticism and fantasy realism. The dramatic lighting, vast landscape, and ethereal atmosphere are reminiscent of Hudson River School painters and Caspar David Friedrich's romantic landscapes. Many elements in the art are reminiscent of visionary art or dreamlike fantasy landscapes.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:54:52.937528"
+}
@@ -0,0 +1,13 @@
+{
+  "hash": "0f0abe8f14a13a22be1114951f19f9e6faafd8ddeeebc3e460da874389d26951",
+  "name": "Artstyle Z1 - WC",
+  "trained_words": [
+    "style",
+    "illustration",
+    "digital illustration",
+    "western comic"
+  ],
+  "description": "Started off as trying to do a western comic style, became abit more expressive and versatile. If you using z-base, then 30-50 steps cfg 3-5, usual stuff. my examples say 25 steps because I used my free tensorart credits to make them and Im capped at 25. sooo.. ya also works with Z-image turbo - use 15-30 steps/CFG 1.1-1.5 and euler discrete flowmatch sampler if you using Z-Image turbo - sigmas are cool. try 0.85 base shift and 1.15 Max shift",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:23:53.139687"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0f3ddee0e7d7c9bf7c1b2223db207227c4e6e6fdbf8d54dc3ebdd6beeba95db3",
+  "name": "Drawing | Tome 1",
+  "trained_words": [
+    "Gotaldosanro art style"
+  ],
+  "description": "NOTE : Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:29:46.270516"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0f78f6e86862d00d13405444dfb1e55a69398620a79a29185b42ca82df0ec40d",
+  "name": "Illustration, sketch and blueprint",
+  "trained_words": [
+    "TechSketch style."
+  ],
+  "description": "This is a compilation of illustration, sketch and similar styles LoRAs.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:53:32.390481"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0fa64c1325569f41f820952b549636ac91d7145a9241713243f63bf21820b222",
+  "name": "watercolor_flux_JG",
+  "trained_words": [
+    "style"
+  ],
+  "description": "The lora model weight is based on 0.6-1.5.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:56:39.496974"
+}
@@ -0,0 +1,8 @@
+{
+  "hash": "0fb42db9f6f75552095b2767a4166e96d97de7cc6e1249b8f999cf53c0527708",
+  "name": "2509 This Person",
+  "trained_words": [],
+  "description": "",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:11:03.076934"
+}
@@ -0,0 +1,12 @@
+{
+  "hash": "0fd02736097f1570da1ea0c0d8e5e584e77e2b0202eb7a8880629d3373850080",
+  "name": "Replace Subject [Klein 4B & 9B]",
+  "trained_words": [
+    "replace the person in Image 1 with the person in Image 2",
+    "replace the man in Image 1 with the man in Image 2",
+    "replace the woman in Image 1 with the woman in Image 2"
+  ],
+  "description": "Allows you to replace a subject in the first control image with a subject in the second control image. The model will skew towards preserving existing details if the secondary control image does not include the relevant details and the prompt leaves them unspecified. For example, if you are using a head/torso image as the new subject, but the original image was zoomed out more and the person being replaced has jeans, the new person will also be wearing jeans unless you specify otherwise. For best results, try to have comparable framing, camera angle, and number of subjects in both images. replace the person in Image 1 with the person in Image 2 replace the man in Image 1 with the man in Image 2 replace the woman in Image 1 with the woman in Image 2 Model Comparisons: Copy Pose will preserve the subject and background in Control 1, while bringing the framing/pose of Control 2 Replace Subject will preserve the framing/pose and background in Control 1, while bringing the subject of Control 2 Replace Scene will preserve the subject and pose in Control 1, while bringing the background scene of Control 2 California AB 2013 Training Data Disclosure This LoRA was fine-tuned using visual data consisting entirely of synthetic still images. The training data may include copyrighted material owned by third parties. No training data was licensed or purchased. This LoRA is provided for non-commercial use only under the terms of its distribution. The dataset consists of over 100 image sets (over 300 images total). This is the total used for training after low quality sets were culled. Dataset was created in 2026. Image data was processed through standard resizing, cropping, normalization, and labeling steps. Synthetic images were included as part of the training dataset. This model is intended for non-commercial, experimental, and educational use. Generated outputs may reflect copyrighted visual styles or themes associated with the underlying training data. Users are responsible for ensuring compliance with applicable copyright law, other intellectual property laws, and all other applicable laws.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:49:40.227310"
+}
@@ -0,0 +1,8 @@
+{
+  "hash": "0fd6ea1b9d3f13c651320b12e3b40e0311d9d40e0877b8cdf5409c50bb00ff35",
+  "name": "Try On Qwen Edit Lora",
+  "trained_words": [],
+  "description": "",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:53:58.915665"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "0fea10d453645038a1d50196a8f5c974cae3945bf069bd2bb0c9b74b471c344a",
+  "name": "Realistic 1st POV",
+  "trained_words": [
+    "1stPOV_flx"
+  ],
+  "description": "LoRA Model: Realistic 1st POV Introducing the Realistic 1st POV LoRA model, designed to create immersive, first-person visual experiences. Whether you're gaming, driving, exploring city streets, or engaging in real-life interactions, this model excels at delivering highly detailed and realistic POV shots that put you directly into the scene. Key Features: Realistic Hand and Controller Views : Perfect for gaming scenarios where you can see your hands on the controller, adding depth to the player’s experience. Action-Packed Visuals : Engage in dynamic action, whether it’s combat or sports, with an intense first-person perspective. Driving Simulations : Feel the adrenaline of racing from a realistic cockpit view with detailed dashboard elements and a clear look at the track ahead. Personal Interactions : Capture intimate moments and personal interactions as if you're in the scene yourself, from casual conversations to close-up engagement with characters. Best Image Sizes: The model delivers optimal results with image ratios of 4:3, 3:2, and 16:9 , ensuring superior detail and depth in a wide variety of contexts. Recommended Parameters: Steps: 20-30 CFG: 1.0 Aspect ratios: 4:3, 3:2, and 16:9 for best results",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:48:55.326873"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "1023efaa0f351e26cbc8cd004d23503d81e6d4262d91319e95455e14b49600d4",
+  "name": "He Tianyou",
+  "trained_words": [
+    "Hetanou style"
+  ],
+  "description": "He Tianyou is a concept artist affiliated with Envar, known for his imaginative visual storytelling and digital illustration. Under the handle Heuu_, he shares a portfolio that blends atmospheric design with character-driven narratives. He is currently available for freelance work and actively showcases his creations on ArtStation. NOTE : Tips for better LoRA expression: Use latent injection instead of empty latent Favor short prompts Avoid using CN or limit its weighting Favor a checkpoint with fp16 precision Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow. All licensing conditions for the Flux Dev model apply. You can find the details here . IMPORTANT NOTE : This model is a tribute to the artist and not an attempt to copy or reproduce his works. Flux1.D is unable to reproduce a graphic universe on which it was trained, the goal is solely to expand Flux's pictorial capabilities. VERY IMPORTANT NOTE : Do not like my models, do not give me buzz, do not follow me, otherwise you will be reported to Civitai for attempted corruption",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:34:34.626818"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "10a21e1eb9abf563578b00d1c01f1fa1b738f62715d8ec740a11572a2c8cb766",
+  "name": "Comic book | Tome 1",
+  "trained_words": [
+    "Bradhamel art style"
+  ],
+  "description": "NOTE : Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:50:12.295166"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "10e5cb891acf4bbc651db1f8081cdd8ae13fada6392e607bb2d971d68a826305",
+  "name": "Dark Infinity's Misc Flux LoRAs",
+  "trained_words": [
+    "ditttdlgnc"
+  ],
+  "description": "This model card is reserved for LoRAs that didn't quite cut it to be released on their own but ones I may want to use on the generator or have others download and test. I am putting it up front that these are random, weird, and sometimes broken models—if you download any to try, feedback is welcome, but results are not guaranteed. Painterly-Realism v2.0 So, fun fact: painterly style and realism are hard to combine. Just because you like two things doesn't mean you should try to shove them together into a single style. I ended up with something that occasionally worked to push realism into digital art but lost the painterly. After multiple training attempts, it either overfitted or lost the painterly style. This was the best of the failures, but it still doesn't do much; it just makes Flux look a bit like a realist painting. Evo-Expressions v3.1 I found a few paintings that inspired me to do an evolved take on expressionist art. Unfortunately, my dataset was extremely limited (4 images with very little variation) and though it turned out very well during training, I quickly discovered its ability to generalize is minimal. Its not a complete failure because it does what it does really well. It is great if you want to make modern, expressionist paint-splattered images of women, but pretty limited if you want to do anything else. It does do some nice animals though. Fractal Flux v1.0 Trained on a huge fractal image, this LoRA can be fantastic, cause the image to look pixelated, or do nothing. It was an experiment using a 1-image LoRA with no captions. Ethereal Rainbow v1.0 Trained in psychedelic art, this LoRA was poorly captioned (because how do you caption that?) but can make some exciting and unusual images. Does it do something? Yep, it causes a radical change for most images, putting color and shapes everywhere. Is it useful? Not really.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:28:09.834538"
+}
@@ -0,0 +1,14 @@
+{
+  "hash": "1199388b465330c7e1d4db71d76807307e37e3dac165d8d21b81fb3fe78a81b0",
+  "name": "Anime Niji Style",
+  "trained_words": [
+    "animeniji",
+    "anime",
+    "niji",
+    "2D flat anime",
+    "NijiCreature"
+  ],
+  "description": "Immerse yourself in a vibrant world where colors and emotions intertwine, bringing forth fantastical characters and stunning landscapes. This LORA captures the essence of anime Niji, showcasing dynamic scenes filled with action and adventure. From heroic battles to magical encounters, every image embodies the enchanting allure of anime, inviting viewers to explore endless possibilities. Get ready to experience a fusion of creativity and storytelling that transcends imagination!",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:22:52.618930"
+}
@@ -0,0 +1,8 @@
+{
+  "hash": "11a7fe8c03fb6e25b163b44db9c753189ee93c3171691904fc9b6784b2fd360d",
+  "name": "Dever Style Transfer (KSTRANSFER)",
+  "trained_words": [],
+  "description": "",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:29:22.772757"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "12020221c1c437e9d456ad041b7b23a181f011d21463bf8013eecd0e0e6fd28c",
+  "name": "Replace Scene [Klein 9B]",
+  "trained_words": [
+    "replace the background in Image 1 with the scene in Image 2"
+  ],
+  "description": "Allows you to replace the background scene in the first control image with the background scene depicted in the second control image. This model is capable of reorienting the camera angle shown in the background to match the one in the original image, but for best results, try to have comparable framing &amp; camera angle. replace the background in Image 1 with the scene in Image 2 Model Comparisons: Copy Pose will preserve the subject and background in Control 1, while bringing the framing/pose of Control 2 Replace Subject will preserve the framing/pose and background in Control 1, while bringing the subject of Control 2 Replace Scene will preserve the subject and pose in Control 1, while bringing the background scene of Control 2 California AB 2013 Training Data Disclosure This LoRA was fine-tuned using visual data consisting entirely of synthetic still images. The training data may include copyrighted material owned by third parties. No training data was licensed or purchased. This LoRA is provided for non-commercial use only under the terms of its distribution. The dataset consists of over 100 image sets (over 300 images total). This is the total used for training after low quality sets were culled. Dataset was created in 2026. Image data was processed through standard resizing, cropping, normalization, and labeling steps. Synthetic images were included as part of the training dataset. This model is intended for non-commercial, experimental, and educational use. Generated outputs may reflect copyrighted visual styles or themes associated with the underlying training data. Users are responsible for ensuring compliance with applicable copyright law, other intellectual property laws, and all other applicable laws.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:49:39.572765"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "12517bedec9525187708f51c2ca7cb29c446633cfae5bb243537a22967a1161d",
+  "name": "[LuisaP❤️] Experimental Lora Pack - Z-IMAGE-TURBO",
+  "trained_words": [
+    "digital art"
+  ],
+  "description": "a lot of experimental models, unammed, scrapped from pinterest or others models. support on kofi if you like my job! https://ko-fi.com/luisacaotica",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:33:58.483296"
+}
@@ -0,0 +1,8 @@
+{
+  "hash": "125c5d8474b4f2a9808767ca467d8622807b47762533fb483db1b1a6295465b2",
+  "name": "Comfyui Portrait Lora 64",
+  "trained_words": [],
+  "description": "",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:26:23.753882"
+}
@@ -0,0 +1,16 @@
+{
+  "hash": "12ea155e67a942e89444ddc1c6ed2fb8cffb9a5ad380a06957e7b214ced5a8c9",
+  "name": "Feet Fix [FLUX] (FLUX)",
+  "trained_words": [
+    "aidmaFeetFix",
+    "photo",
+    "feet",
+    "tool",
+    "realistic",
+    "realism",
+    "real feet"
+  ],
+  "description": "v0.1 start with 0.3/0.4 and go higher",
+  "source": "civitai",
+  "imported_at": "2026-07-23T14:50:33.148158"
+}
@@ -0,0 +1,17 @@
+{
+  "hash": "12ee4189591aadf6a41a3f74bb80daff0e62c3cbdb4e7707d501cccca5508c21",
+  "name": "Dark Fantasy Style [FLUX] - Training Comparison (rapid & normal) (FLUX)",
+  "trained_words": [
+    "aidmaDarkfantasy",
+    "scene",
+    "fantasy",
+    "characters",
+    "dark fantasy style",
+    "dark fantasy",
+    "style",
+    "dark"
+  ],
+  "description": "v0.1 trained with my basic Lora training settings its the same Dataset its the way better Version in my eyes. Try combine both!",
+  "source": "civitai",
+  "imported_at": "2026-07-23T14:50:23.147942"
+}
@@ -0,0 +1,16 @@
+{
+  "hash": "1339408d54b7738fa70b1e735e7a68398402b0089565ba9ac225baeb7f974f67",
+  "name": "Comics Factory | Tome 2 (V2T2)",
+  "trained_words": [
+    "Gavenine art style",
+    "painting",
+    "portraiture",
+    "drawing",
+    "portrait art",
+    "portrait",
+    "style"
+  ],
+  "description": "Steps : 8 Sampler : Seed_3 Scheduler : Normal Weighting : around 0.75",
+  "source": "civitai",
+  "imported_at": "2026-07-22T23:27:07.157090"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "1398e09a41a20e8c01acd13313c81e8d95826da89ce5f9af5874eeaf626bdcd8",
+  "name": "Charcoal NSFW - CE",
+  "trained_words": [
+    "An artistic charcoal sketch"
+  ],
+  "description": "The Renaissance and Rubens The Renaissance ushered the world into a glorious period for art. In particular, its depiction of the nude form changed art forever. Coming after the Renaissance, Peter Paul Rubens, a master of the Baroque era, approached the nude form with a distinctive vitality and celebration of physicality that has become synonymous with his name. His depictions are characterized by a robust, dynamic sensuality, blending classical ideals of beauty with a palpable realism that honors the natural human body. It's impossible to deny the beauty of the nude in art and charcoal drawings are no exception. Charcoal art Monochrome charcoal nude drawings possess a timeless and evocative beauty, rooted in their simplicity and emotional depth. The stark black-and-white palette strips the subject down to its essence, allowing the viewer to focus on form, texture, and the subtle interplay of light and shadow. The velvety richness of charcoal creates a sense of intimacy, emphasizing contours and soft gradations that mimic the warmth and complexity of the human body. The medium's ability to shift from crisp, bold lines to ethereal smudges mirrors the fragility and strength inherent in human anatomy. Every stroke speaks of raw expression, often revealing more about the artist's hand and emotions than the subject itself. The imperfections—smudges, uneven edges, and tonal variations—lend a sense of life and movement, as if the figure is emerging from the page. Monochrome also brings a universality to the work, distilling it into a study of form, emotion, and timelessness. The absence of color removes distractions, inviting deeper contemplation of the figure's vulnerability, strength, and innate humanity. This LoRA To maximize the abilities of the LoRA, it was trained on NSW images.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:24:58.060256"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "13c45b82589c082f52df760ad707ff09ce0d17157bf248a8551e78b57d6ca525",
+  "name": "Lea Seydoux (2014-2018) [FLUX.1D]",
+  "trained_words": [
+    "Lea Seydoux"
+  ],
+  "description": "",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:40:04.859559"
+}
@@ -0,0 +1,13 @@
+{
+  "hash": "13e2a07b236f12fd9804f113c709335bfbb08fedf57947f3761abb498cc7f67a",
+  "name": "ZIT - ARTManiac",
+  "trained_words": [
+    "drawing",
+    "art",
+    "style",
+    "z image turbo"
+  ],
+  "description": "ZIT - ARTManiac A powerhouse illustration LoRA for Z-Image-Turbo that delivers stunning, hand-drawn results. It's self-sufficient and works like a charm at 0.85 strength, but also plays nicely with other LoRAs. Just prompt and paint. No trigger word needed. The model works great with other LoRAs as a base — if you set the model strength to 0.5 + your LoRA or LoRAs, the results will be excellent (in most cases)",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:23:51.860092"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "1440c4abe3220b665e368fca6653fc2fcfb16af49ab28777446141c5ea6e56af",
+  "name": "Niji",
+  "trained_words": [
+    "Niji art style"
+  ],
+  "description": "NOTE : Base model : Z Image Turbo &amp; Flux1 . Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:45:47.913972"
+}
@@ -0,0 +1,14 @@
+{
+  "hash": "1456be8d1b8d25f503457ed7de43657781bb406caea95afe3f3324889a8cdb0a",
+  "name": "Antique Golden Style - CE",
+  "trained_words": [
+    "art",
+    "style",
+    "painting",
+    "golden",
+    "style,"
+  ],
+  "description": "The Antique Golden Style LoRA was trained on images with rich golden hues to produce a particular style, characterized by colorful sunsets and an antique quality. V02 Version 1 lacked some flexibility, particularly when it came to indoor scenes. I produced a new set of training images to create version 2. Overall, it seems to retain the same characteristics. but with improved results. Please share your creations. I would love to see how you have used the LoRA.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:23:20.452321"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "146b68fd53fd2fb0a099230d77e04d1dedf32af023455008d6a9234da167079c",
+  "name": "Alejandro Burdisio",
+  "trained_words": [
+    "Art by Alejandro Burdisio"
+  ],
+  "description": "Alejandro Burdisio, also known as \"Burda,\" is an Argentine artist celebrated for his imaginative and humorous illustrations. His work often blends elements of the past and future, creating surreal environments that evoke nostalgia and curiosity. Burdisio's \"Junk Universe\" series is particularly notable, showcasing fantastical scenes where iconic buildings and vehicles are transformed into floating islands in polluted urban landscapes. His background in architecture and design heavily influences his artistic style, which combines meticulous geometric accuracy with a vibrant, cinematic atmosphere. IMPORTANT NOTE : This model is a tribute to the artist and not an attempt to copy or reproduce his works. Flux1.D is unable to reproduce a graphic universe on which it was trained, the goal is solely to expand Flux's pictorial capabilities. The idea is to use this model, combined with others, to create new styles of digital art expression. \"Nothing is lost, nothing is created, everything is transformed\" is an apocryphal quote from Antoine Lavoisier. We are somewhat in this vision. Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow. All licensing conditions for the Flux Dev model apply. You can find the details here .",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:17:28.824072"
+}
@@ -0,0 +1,19 @@
+{
+  "hash": "14f75ad89dcd2302ac756ef48c89cd9f2332bb23500246da978b8ff23306c21c",
+  "name": "[Flux Detailer] MysticFantasy Style",
+  "trained_words": [
+    "anime",
+    "render",
+    "style",
+    "woman",
+    "fantasy",
+    "man",
+    "realistic",
+    "rpg",
+    "detailer",
+    "styles"
+  ],
+  "description": "Unleash the power of imagination with this lora, a great tool for crafting intricate, fantasy-rich visuals. Whether you're an artist, storyteller, or creative enthusiast, this lora transforms your concepts into stunning, detailed masterpieces. This model is designed to enhance your work, adding layers of depth and nuance to every image. With its fantasy-driven bias, this lora brings your dreams to life, be it magical worlds, mythical creatures, or epic landscapes. Elevate your creative flow, and let your visuals resonate with rich detail and captivating beauty. Let it guide your journey into boundless fantasy! It is essentially a detailer with fantasy bias. Recommended Usage: Checkpoint: flux1-dev Strength: 0.8~1.0 (adjust depending on the number of details needed for the best results) Sampling Method: Euler Scheduler Type: Simple CFG Scale: 3 Steps: 25-35 Feel free to share your creations and feedback so I can improve this model and continue contributing to the creative community!",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:45:09.789317"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "151227483e74d9ad0e30fd41e3aac52ddc32a75177e006d106a29f75dbc5d26d",
+  "name": "ADONIS (Base (v2.1))",
+  "trained_words": [
+    "uhdmanscale"
+  ],
+  "description": "Main and Alt is now Base &amp; Refine Base and Refine models are now used together, with Base setting the image and Refine finishing the details. There should be very little shifting when using the models in this way. The models have been block edited to have slightly less effect on color/saturation, as the Main and Alt version tended to undersaturate the outputs to an extreme degree. The new workflow will be posted with the changes in place.",
+  "source": "civitai",
+  "imported_at": "2026-07-22T22:48:41.650477"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "1540efa433572351ce245200ae8be3febcdc22ab51ed44eb3c78af3dbb1c89fa",
+  "name": "Luis Royo Style - Krea 2",
+  "trained_words": [
+    "painting in the style of luis royo"
+  ],
+  "description": "This LoRA captures the iconic, sensual, and haunting dark fantasy art style of Spanish master illustrator Luis Royo . Perfect for generating powerful warriors, gothic sci-fi characters, and melancholic post-apocalyptic scenes. It excels at reproducing his signature soft-focus airbrush textures, highly detailed biomechanical or metallic armor, and hyper-realistic pale skin tones set against dark, atmospheric backgrounds. ### 🚀 What's New in V2? * Expanded Dataset: Upgraded to 118 high-quality, sharp curated images capturing his book covers and portfolios (*III Millennium*, Dead Moon , etc.). * Flawless Shading: Massively improved transitions for smooth skin tones, soft atmospheric mist, and delicate metallic surfaces. * Optimized Selection: Extracted from the perfect sweet spot of the training curve (**Step 2,596**) to prevent overfitting and ensure maximum flexibility. ### ⚙️ Training Details &amp; Dataset Info: * Dataset Size: 118 Images (fully captioned) * Training Resolution: 512 x 512 pixels (highly scalable on modern DiT architectures) * Total Training Steps Used: 2,596 Steps (extracted from backup for optimal coherence) ### 🔧 Recommended Generation Settings: * Trigger Words / Phrase: painting in the style of luis royo ### 📝 Prompting Tips: To invoke the ultimate Luis Royo atmosphere, combine the trigger phrase with his signature thematic keywords: * painting in the style of luis royo, airbrush on canvas, pale skin, soft monochrome shading, gothic leather armor, biological machinery, mechanical wings, desolate ash wasteland, melancholic fantasy artwork. If you enjoy the unique look of this V2, please drop a review and share your generations below. Let's bring back the dark elegance of classic 90s fantasy art!",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:43:05.587641"
+}
@@ -0,0 +1,14 @@
+{
+  "hash": "1554f3a6c21974acb0c163232e18f728eabfe4b052db53768a63891fc02dda87",
+  "name": "Antique Golden Style - CE",
+  "trained_words": [
+    "art",
+    "style",
+    "painting",
+    "golden",
+    "style,"
+  ],
+  "description": "The Antique Golden Style LoRA was trained on images with rich golden hues to produce a particular style, characterized by colorful sunsets and an antique quality. V02 Version 1 lacked some flexibility, particularly when it came to indoor scenes. I produced a new set of training images to create version 2. Overall, it seems to retain the same characteristics. but with improved results. Please share your creations. I would love to see how you have used the LoRA.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:23:15.912782"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "1561f24768f87a3f089ce401d0af38f1de3ec08579674d911b7468b69c603c42",
+  "name": "Nipples FLUX",
+  "trained_words": [
+    "small nipples"
+  ],
+  "description": "Nipples FLUX Because nipples comes in several shapes and colors, this time the \"jewel of the crown\" returns for FLUX. Even when FLUX is still quite young and it struggles with nudity I wanted to publish a first version of these models to help the model to improve it's lewd capabilities and aid those who seek either realism, representation or a special flavor to their generations. Just like the SDXL Nipple model , I will be adding version for each kind of nipples. Enjoy!",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:45:57.069318"
+}
@@ -0,0 +1,11 @@
+{
+  "hash": "15a5338a1e4e3970cba4a2dc07edc7345b0b8d65c615d058c1d9cd6085a8e348",
+  "name": "RealComic",
+  "trained_words": [
+    "pingtu style",
+    "illustration-fen"
+  ],
+  "description": "Preface This is a model that stumped me just by naming it. It has a realistic style but the sense of lines is very prominent. It has delicate skin coloring, while other contents are rather rough, but the fine lines remain unchanged. The first time this style popped up in my mind, it made me extremely intimate and delighted. My yearning for this style made me determined to create it, but I didn't know how to define it. If there are any friends who know, please give me some advice. I will expand the training and define appropriate trigger words for it. Now, please allow me to temporarily call it realistic comics for the time being. I hope this model can convey my joy. Feel the fun of AI. Have a good time. The Characteristics of \"RealComic\" 1、First of all, its positioning is an illustration model and it is very good at drawing fashionable female illustrations. 2、Its understanding of animals seems to be between comics and meticulous brushstrokes, which are both cute and have delicate lines. 3、Its depiction of the environment tends to be flat painting, which can better highlight the main body, and the delicate lines can well unify the two. Parameter Recommendations The example images use the default parameters Weights ：0.6~0.9（default 0.9） sizes：768/1024/1536（default 1024） Guidance Conditions ：2.5~3.5（default 3.5） Steps ：20~40（Using the turbo model, so...the default step length is 8 steps） Sampler ：euler（simple） Trigger Words：pingtu style、illustration-fen To achieve the best output effect, it is recommended to be paired with the exclusive workflow OK! That's all for this time. If you like my work, please give it a like or buy me a coffee: ☕ https://ko-fi.com/vjleoliu ☕ I also accept private customization Thank you for reading up to here. English is not my native language. The above is translated by AI. If there is anything inappropriate, welcome to correct me. Finally, I hope you have fun！ 👉👉👉My model library👈👈👈",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:48:23.915803"
+}
@@ -0,0 +1,14 @@
+{
+  "hash": "15b88a24610af5e8baff70c16a6c83c9cce7032fec880db7772a035dc79c24d2",
+  "name": "Dorota Piotrowiak (SDXL/QWEN/Z IMAGE) (ZIT)",
+  "trained_words": [
+    "DorotaPietrowiak",
+    "portrait",
+    "drawing",
+    "style",
+    "painting"
+  ],
+  "description": "",
+  "source": "civitai",
+  "imported_at": "2026-07-23T08:47:13.157187"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "15c21d55c53cc7c08f7a5dcb2cba0f16c4e922558fd579fb152c56899a003d56",
+  "name": "CW Home R - Design - ZIT",
+  "trained_words": [
+    "homer01"
+  ],
+  "description": "Finding all my models or profile elsewhere than Civitai is without my consent ! Please don't repost my files. Send people to my Civitai profile, thanks :) - Welcome Home R ! Home R is a group of loras about architecture and design. -- What will it do ? Create interiors (Cyberpunk, Science fiction, Baroque, and more) Create outdoors (houses, design environments) Create some design objects Create some old science objects Realistic and Anime The ZIT version (also exist for Flux and Illustrious with a little different dataset) can be combined with some of my other loras for very nice results : Home of The Ancients - Background / Character Creator : Will do GREAT with interiors at strenghth 1, giving more details and some nice surprises but it won't do well with outdoor... but I didn't test much that part, so maybe reducing the strength might help. Can also be used to do Anime : https://civitai.com/models/2201479?modelVersionId=2516060 EFFECTS : There are some effects built in this lora and adding more can be fun. But at 1 strength, it will kill the composition and give ugly results... So lower it to 0.4 and relax : https://civitai.com/models/2202300?modelVersionId=2479630 -- HOW TO USE : Strength : 1 tested Steps : 15 - 20 tested Checkpoints : Any (anime and realistic in the dataset but ZIT will do realistic) Adetailer : not tested -- The main trigger word is : homer01 -- Some effects are built in. See pictures for prompts ;) Have fun ! :)",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:25:35.915132"
+}
@@ -0,0 +1,16 @@
+{
+  "hash": "1607c11f0106dcb6a4d1e2843e2673a98ae3fc2001d04955f7f869b81a36c5ad",
+  "name": "anicomics",
+  "trained_words": [
+    "anime",
+    "digital art",
+    "comics",
+    "style",
+    "cartoon",
+    "2.5d",
+    "anicomics"
+  ],
+  "description": "recommend parameters: model Flux.1 Model Family_Black Forest Labs_FLUX.1-dev-fp8. guidance 3.5-8 cfg 1 clip last layer -2 lora strength 0.8-1.2 Clip: t5xxl_fp8_e4m3fn, ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF P.S. sometimes has some problems with anatomy, broken fingers, extra arms etc",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:17:44.803060"
+}
@@ -0,0 +1,10 @@
+{
+  "hash": "161d99d66d2c22710daf959ec839776680b67a2a0f1e36eecb8923c2efafc23d",
+  "name": "Jon Foster",
+  "trained_words": [
+    "JoFote style"
+  ],
+  "description": "Jon Foster is an American illustrator, painter, and sculptor known for his evocative, often dark-toned artwork in fantasy and science fiction. A graduate of the Rhode Island School of Design (1989), he’s created covers for comic books (DC Comics, Dark Horse), novels (Brandon Sanderson’s Mistborn , Timothy Zahn’s Dragonback series), and role-playing games like Dungeons &amp; Dragons . His oil paintings are digitally enhanced, blending traditional technique with modern effects. Foster has earned multiple awards from Spectrum: The Best in Contemporary Fantastic Art and teaches at The Illustration Academy. NOTE : Showcase images were created with ComfyUI and are in PNG, include metadata &amp; workflow. All licensing conditions for the Flux Dev model apply. You can find the details here . IMPORTANT NOTE : This model is a tribute to the artist and not an attempt to copy or reproduce his works. Flux1.D is unable to reproduce a graphic universe on which it was trained, the goal is solely to expand Flux's pictorial capabilities. VERY IMPORTANT NOTE : Do not like my models, do not give me buzz, do not follow me, otherwise you will be reported to Civitai for attempted corruption",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:38:42.412516"
+}
@@ -0,0 +1,13 @@
+{
+  "hash": "163ddefd790142ed8b64516f4bf6e69f14e0a9d5a6427bb0f4d13fe6b42a3901",
+  "name": "Reptile Skin - CE",
+  "trained_words": [
+    "style",
+    "skin",
+    "reptile",
+    "lizard"
+  ],
+  "description": "Please share your creations. I would love to see how you have used the LoRA. Weight range: 0.7 - 1.2, depending on the intensity of effect desired. Start around 1.0 and go from there.",
+  "source": "sidebar",
+  "imported_at": "2026-07-22T21:49:46.884410"
+}
--- a/Show More
+++ b/Show More