Any checkpoint can now be in the generator. Anything already loaded works for everyone; members load the new ones free for now, with a faster lane and Boost to jump the queue.

Any Model, Any Time: Load It Into the Generator Yourself

We rebuilt the trainer. Watch your run as it trains, generate with an epoch before it's done, and compare epochs side by side. It's in beta, and you switch it on yourself in your preferences.

Training Studio: Watch It Train, Generate As It Goes

A training and content contest with over 2 Million Buzz in prizes and 50% off H3 generation for the duration of the contest.

The Civitai H3 Contest: 2 Million Buzz Up For Grabs

Styles are trained on synthetic data and do not copy the styles of artists!Photo 2 - is trained on real data (Dataset from Unsplash)[M] Merged LoRAsRecommended LoRA Strength (Weight): 0.8-1Preview generated without using ADetailer &amp; Hires. fix

Abstract Painting

Repeats: 10Epoch: 12Image Count: 20Network Rank (Dimension): 32Network Alpha: 16Batch size: 1Clip skip: 1Training steps: 2400Resolution: 1024x1024Train Resolution: 1024,1024Model: ponyDiffusionV6XL_v6LR Scheduler: cosine_with_restartsOptimizer: AdamW8bitLearning rate: 0,0005Text Encoder learning rate: 0,00005Unet learning rate: 0,0005Captioning: WD14 Captioning (SmilingWolf/wd-v1-4-moat-tagger-v2) + EditRecommended LoRA Strength (Weight): 0.7-0.8Trigger Words: sketch, monochrome, greyscale,LoRA is trained on images created by me using ideogram.ai

Sketch Illustration

Repeats: 10Epoch: 12Image Count: 20Network Rank (Dimension): 32Network Alpha: 16Batch size: 1Clip skip: 1Training steps: 2400Resolution: 1024x1024Train Resolution: 1024,1024Model: ponyDiffusionV6XL_v6LR Scheduler: cosine_with_restartsOptimizer: AdamW8bitLearning rate: 0,0005Text Encoder learning rate: 0,00005Unet learning rate: 0,0005Captioning: WD14 Captioning (SmilingWolf/wd-v1-4-moat-tagger-v2) + EditRecommended LoRA Strength (Weight): 0.7-0.8Trigger Words: painterly, traditional media, realistic,LoRA is trained on images created by me using ideogram.ai

Dream Painting

Repeats: 10Epoch: 5Image Count: 50Network Rank (Dimension): 32Network Alpha: 16Batch size: 1Clip skip: 1Training steps: 2500Resolution: 768x1024Train Resolution: 1024,1024Model: ponyDiffusionV6XL_v6LR Scheduler: cosine_with_restartsOptimizer: AdamW8bitLearning rate: 0,0005Text Encoder learning rate: 0,00005Unet learning rate: 0,0005Captioning: WD14 Captioning (SmilingWolf/wd-v1-4-moat-tagger-v2) + EditRecommended LoRA Strength (Weight): 0.7-0.8Trigger Words: watercolor \(medium\), traditional media,

Watercolor Anime

Repeats: 10Epoch: 5Image Count: 50Network Rank (Dimension): 32Network Alpha: 16Batch size: 1Clip skip: 1Training steps: 2500Resolution: 768x1024Train Resolution: 1024,1024Model: ponyDiffusionV6XL_v6LR Scheduler: cosine_with_restartsOptimizer: AdamW8bitLearning rate: 0,0005Text Encoder learning rate: 0,00005Unet learning rate: 0,0005Captioning: WD14 Captioning (SmilingWolf/wd-v1-4-moat-tagger-v2) + EditRecommended LoRA Strength (Weight): 0.7-0.8Trigger Words: watercolor \(medium\), traditional media, realistic,

Watercolor Painting

Repeats: 10Epoch: 4Image Count: 72Network Rank (Dimension): 32Network Alpha: 16Batch size: 1Clip skip: 1Training steps: 2880Resolution: 1024x1024Train Resolution: 1024x1024LR Scheduler: cosine_with_restartsOptimizer: AdamW8bitLearning rate: 0,0005Text Encoder learning rate: 0,00005Unet learning rate: 0,0005Model: ponyDiffusionV6XL_v6Captioning: WD14 Captioning (SmilingWolf/wd-v1-4-moat-tagger-v2)Trigger Words: painterly, faux traditional media, realistic, Recommended LoRA Strength (Weight): 0.7-1The same dataset as that of Faux Oil Painting, only less contrast and saturation

Faux Oil Painting Soft

Repeats: 10Epoch: 4Image Count: 72Network Rank (Dimension): 32Network Alpha: 16Batch size: 1Clip skip: 1Training steps: 2880Resolution: 1024x1024Train Resolution: 1024x1024LR Scheduler: cosine_with_restartsOptimizer: AdamW8bitLearning rate: 0,0005Text Encoder learning rate: 0,00005Unet learning rate: 0,0005Model: ponyDiffusionV6XL_v6Captioning: WD14 Captioning (SmilingWolf/wd-v1-4-moat-tagger-v2)Trigger Words: painterly, faux traditional media, realistic, Recommended LoRA Strength (Weight): 0.7-1LoRA is trained on images created by me using ideogram.ai (The images have been enhanced using StableSR)

Faux Oil Painting

Repeats: 20Epoch: 20Image Count: 22Network Rank: 32Network Alpha: 16Batch size: 1Clip skip: 1Training steps: 3200Resolution: 640x1024Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6Captioning: WD14 Captioning (SmilingWolf/wd-v1-4-convnextv2-tagger-v2)Trigger Words: flat color, &amp; lineart, monochrome, greyscale,Recommended LoRA Strength: 0.7-1

LineArt Mono

Concept Art DarkSide is a merge of 3 models0.30 - Concept Art Dark0.35 - Concept Art Night (Unpublished)0.35 - Concept Art Night Not Edited (Unpublished)Recommended LoRA Strength: 0.7-1For one reason or another, I don't publish some styles. I don't always manage to create a good style the first time, sometimes I have to merge several models to get the style I want.kohya_ss does not allow to merge models with different Network Dimension (Rank). That's why I don't change the LoRA training settings.

Concept Art DarkSide [M]

Concept Art Mixture + Concept Art Mixture Brush 50/50 = Concept Art UltimatumConcept Art Twilight + Concept Art Eclipse 50/50 = Concept Art Mixture (Unpublished)Concept Art Mixture Brush (Unpublished)Same data set as Concept Art Brush but trained on a mix of Twilight and EclipseRecommended LoRA Strength: 0.7-1

Concept Art Ultimatum [M]

Repeats: 20Epoch: 2Image Count: 70Network Rank: 32Network Alpha: 16Batch size: 1Clip skip: 1Training steps: 2800Resolution: 1024x1024Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6Captioning: WD14 Captioning (SmilingWolf/wd-v1-4-moat-tagger-v2)Trigger Words: concept art, digital art, realistic,Recommended LoRA Strength: 0.7-1LoRA is trained on images created by me using ideogram.ai

Concept Art Brush

Concept Art Eclipse is a merge of 3 models0.30 - Concept Art 20.35 - Concept Art Dark 2 (Unpublished)0.35 - Concept Art Negative 2 (Unpublished)LoRA Weight: [0.8-1]

Concept Art Eclipse [M]

Repeats: 20Epoch: 20Image Count: 14Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 2800Resolution: 1024x1024Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6Captioning: WD14 Captioning (SmilingWolf/wd-v1-4-moat-tagger-v2)Trigger Words: concept art, realistic,LoRA Weight: [0.7-1]Same dataset as Concept Art but edited, more detail in the lights and a little more texture.

Concept Art 2

Eldritch Oil is a merge of 3 models0.35 - Oil Painting Sharp0.35 - Impressionism Oil Painting0.30 - Palette Knife Painting

Eldritch Oil [M]

Repeats: 20Epoch: 10Image Count: 20Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 2000Resolution: 704x1024, 792x1024Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6Captioning: WD14 Captioning + Edit (SmilingWolf/wd-v1-4-moat-tagger-v2)Trigger Words: oil painting, traditional media, realistic,LoRA Weight: [0.7-1]This Style is trained on the images created by this LoRA<a target="_blank" rel="ugc" href="https://civitai.com/models/336656/eldritch-palette-knife-painting-oil-painting-style">https://civitai.com/models/336656/eldritch-palette-knife-painting-oil-painting-style</a>

Palette Knife

Repeats: 20Epoch: 5Image Count: 58Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 2900Resolution: 704x1024, 792x1024, 1024x792Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6Captioning: WD14 Captioning + Edit (SmilingWolf/wd-v1-4-moat-tagger-v2)Trigger Words: oil painting, traditional media, realistic,LoRA Weight: [0.8-1]This Style is trained on the images created by this LoRA<a target="_blank" rel="ugc" href="https://civitai.com/models/312341/eldritch-impressionism-oil-painting">https://civitai.com/models/312341/eldritch-impressionism-oil-painting</a>

Impressionism Oil

Repeats: 20Epoch: 5Image Count: 56Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 2800Resolution: 704x1024Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6Captioning: WD14 Captioning + Edit (SmilingWolf/wd-v1-4-moat-tagger-v2)Trigger Words: oil painting, traditional media, realistic,LoRA Weight: [0.8-1]This Style is trained on the images created by this LoRA<a target="_blank" rel="ugc" href="https://civitai.com/models/127139/classipeintxl-oil-paint-oil-painting-style">https://civitai.com/models/127139/classipeintxl-oil-paint-oil-painting-style</a>

Oil Painting Sharp

Repeats: 20Epoch: 10Image Count: 24Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 2400Resolution: 768x1024Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6Captioning: WD14 Captioning + Edit (SmilingWolf/wd-v1-4-moat-tagger-v2)Trigger Words: gothic art, oil painting, traditional media, realistic,LoRA Weight: [0.7-1]

Gothic Art 2

Smooth Night + Cold Night = Smooth Anime Night

Smooth Anime Night [M]

Repeats: 20Epoch: 20Image Count: 12Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 2400Resolution: 576x832Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 Captioning: SmilingWolf/wd-v1-4-moat-tagger-v2Trigger Words: dark theme, low light,LoRA Weight: [0.8-1]

Smooth Night

Repeats: 20Epoch: 20Image Count: 16Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 3200Resolution: 960x1024Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 Captioning: SmilingWolf/wd-v1-4-moat-tagger-v2Trigger Words: dark theme, low light,LoRA Weight: [0.8-1]With the use of Trigger Words the image becomes darker and more like night, same with Cold Night

Summer Night

Repeats: 20Epoch: 20Image Count: 16Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 3200Resolution: 960x1024Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 Captioning: SmilingWolf/wd-v1-4-moat-tagger-v2LoRA Weight: [0.8-1]Same dataset only with reduced contrast, a little more detail in the highlights and shadows and more Training steps

Summer Days 2

Cold Oil + Gothic Art Sharp = Cold Oil GothicGothic Art Sharp is the same as Gothic Art only sharper, even too sharper for this reason and not published

Cold Oil Gothic [M]

Repeats: 20Epoch: 5Image Count: 56Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 2800Resolution: 704x1024Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6Captioning: WD14 Captioning + Edit (SmilingWolf/wd-v1-4-moat-tagger-v2)Trigger Words: oil painting, traditional media, realistic,LoRA Weight: [0.8-1]Cold Oil is whiter cooler less yellow unlike Oil Painting and not much more contrast in the shadowsWithout Trigger Words the style isn't as strong it still looks good but with Trigger Words it looks like real Oil PaintingCold Oil does not create low light images LoRA is in no way related to Cold Night other than Cold in the nameThis Style is trained on the images created by this LoRA And the editing by me<a target="_blank" rel="ugc" href="https://civitai.com/models/127139/classipeintxl-oil-paint-oil-painting-style">https://civitai.com/models/127139/classipeintxl-oil-paint-oil-painting-style</a>

Cold Oil [M]

Repeats: 20Epoch: 3Image Count: 100Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 3000Resolution: 768x1024Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 Captioning SmilingWolf/wd-v1-4-moat-tagger-v2Trigger Words: dark theme, low light,LoRA Weight: [0.8-1]This is Night Version of Anime StyleWithout using Trigger Words, the image is a bit lighter and almost no different, but I still recommend using Trigger Words

Cold Night

Repeats: 5Epoch: 4Image Count: 300Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 3000Resolution: 768x1024Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6Captioning: WD14 Captioning + Edit (SmilingWolf/wd-v1-4-moat-tagger-v2)Trigger Words: raw, photo, realistic,LoRA Weight: [0.8-1]Without the tokens raw, photo, realistic, the model will generate 2.5D-3D and sometimes 2D styles, these tokens should be at the beginning after the score, if you can't get a realistic style, you're doing something wrong try to change the promptThe preview should show that the first image is with Trigger Words and the second image is just with LoRAScore, Trigger Words, Prompt

Photo 2

Repeats: 20Epoch: 12Image Count: 20Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 2400Resolution: 768x1024Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 CaptioningSmilingWolf/wd-v1-4-moat-tagger-v2LoRA Weight: [0.8-1]

Rainbow

Repeats: 20Epoch: 6Image Count: 24Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 1440Resolution: 832x1024+1024x768Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 CaptioningSmilingWolf/wd-v1-4-moat-tagger-v2LoRA Weight: [0.7-1]This Style is trained on the images created by this LoRA<a target="_blank" rel="ugc" href="https://civitai.com/models/303233/eldritch-digital-art">https://civitai.com/models/303233/eldritch-digital-art</a>

Digital Art

Smooth 2 + Anime 2 = Smooth Anime 2

Smooth Anime 2 [M]

Repeats: 20Epoch: 3Image Count: 100Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 3000Resolution: 768x1024Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 CaptioningSmilingWolf/wd-v1-4-moat-tagger-v2LoRA Weight: [0.7-0.8]

Anime 2

Repeats: 20Epoch: 20Image Count: 12Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 2400Resolution: 576x832Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 CaptioningSmilingWolf/wd-v1-4-moat-tagger-v2LoRA Weight: [0.7-0.8]

Smooth 2

Concept Art Twilight - Concept Art + Concept Art Dark (Unpublished) + Concept Art Negative (Unpublished) 35/35/30LoRA Weight: [0.8-1]

Concept Art Twilight [M]

Repeats: 20Epoch: 10Image Count: 14Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 1400Resolution: 1024x1024Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 CaptioningSmilingWolf/wd-v1-4-moat-tagger-v2LoRA Weight: [0.8-1]

Concept Art

Oil Painting + Gothic ArtLoRA Weight: [0.8-1]

Oil Gothic [M]

Repeats: 20Epoch: 12Image Count: 10Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 1200Resolution: 768x768Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 CaptioningSmilingWolf/wd-v1-4-moat-tagger-v2LoRA Weight: [0.8-1]

Gothic Art

Repeats: 20Epoch: 10Image Count: 16Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 1600Resolution: 960x1024Train Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 CaptioningSmilingWolf/wd-v1-4-moat-tagger-v2LoRA Weight: [0.8-1]

Summer Days

Repeats: 20Epoch: 20Image Count: 8Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 1600Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 CaptioningSmilingWolf/wd-v1-4-convnextv2-tagger-v2LoRA Weight: [0.6-0.8]This Style is trained on the images created by this LoRA<a target="_blank" rel="ugc" href="https://civitai.com/models/16014?modelVersionId=28907">https://civitai.com/models/16014?modelVersionId=28907</a>

Line Art

Repeats: 20Epoch: 10Image Count: 22Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 2200Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 CaptioningSmilingWolf/wd-v1-4-convnextv2-tagger-v2LoRA Weight: [0.8-0.1]

Photo

Repeats: 20Epoch: 5Image Count: 56Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 2800Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 CaptioningSmilingWolf/wd-v1-4-convnextv2-tagger-v2LoRA Weight: [0.8-1]This Style is trained on the images created by this LoRA<a target="_blank" rel="ugc" href="https://civitai.com/models/127139/classipeintxl-oil-paint-oil-painting-style">https://civitai.com/models/127139/classipeintxl-oil-paint-oil-painting-style</a>

Oil Painting

Repeats: 20Epoch: 10Image Count: 14Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 1400Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 CaptioningSmilingWolf/wd-v1-4-convnextv2-tagger-v2LoRA Weight: [0.7-0.8]This Style is trained on the images created by this LoRA<a target="_blank" rel="ugc" href="https://civitai.com/models/159693?modelVersionId=179622">https://civitai.com/models/159693?modelVersionId=179622</a>

Smooth Anime [M]

Repeats: 20Epoch: 20Image Count: 8Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 1600Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 CaptioningSmilingWolf/wd-v1-4-convnextv2-tagger-v2LoRA Weight: [0.5-0.7]

Anime

Repeats: 20Epoch: 20Image Count: 8Network Rank: 32Network Alpha: 16Batch size: 2Clip skip: 1Training steps: 1600Resolution: 1024x1024Model: ponyDiffusionV6XL_v6WD14 CaptioningSmilingWolf/wd-v1-4-convnextv2-tagger-v2LoRA Weight: [0.6-0.7]

Not Artists Styles for Pony Diffusion V6 XL