<h3 id="sierra">Sierra</h3>This is made of over 100 images of the same dataset but different in caption style, which led to generating a consistent face. It is meant to be used mainly with <a target="_blank" rel="ugc" href="https://civarchive.com/models/133005/juggernaut-xl">Juggernaut XL</a> and for spicy images with <a target="_blank" rel="ugc" href="https://civarchive.com/models/443821?modelVersionId=2727742">CyberRealistic Pony</a>.Training settings were influenced by how Juggernaut XL is. with bleeding in mind while captioning, the steps were as high as 5 repetitions. Juggernaut XL works very well with slightly underfit LoRAs. Use quality tags at the end of the descriptions for improving the image quality. (strength 0.86, go lower for complex poses so the base model helps out. 25 - 30 steps, Quality 60 steps) <h3 id="no-more-same-face"><a target="_blank" rel="ugc" href="https://civarchive.com/models/2552453?modelVersionId=2868545">No More Same Face</a></h3> This is my improved remake of the original No_More_Sameface_v3.The old v3 was trained on only 48 images and was later deleted by the uploader (user: 9__9). I used it a lot and decided to remake it with a much better dataset.Dataset (no AI, face only): 594 open-source real photos in 1024x1024 of diverse young women aged 18 - 35 (filtered with DeepFace | True random‑face LoRA needs at least 1.2 k diverse images. I had to remove most of the dataset because of the CivitAI trainer limitation of max 10 k steps).Trigger word: <code>r4nd0mf4c3</code> (weight: min 0.65, recommended 0.86, max 1.0)Published model is from epoch 7. you can download <a target="_blank" rel="ugc" href="https://drive.proton.me/urls/1XKY1A1SQ4#aFXnQEkJDFYL">other epochs here</a><pre><code>
{
 "lr": 0.0005,
 "engine": "ai-toolkit",
 "epochs": 8,
 "ecosystem": "sdxl",
 "keepTokens": 1,
 "networkDim": 32,
 "numRepeats": 8,
 "resolution": 1024,
 "lrScheduler": "cosine",
 "minSnrGamma": 5,
 "noiseOffset": 0.1,
 "networkAlpha": 16,
 "optimizerType": "adamw8bit",
 "shuffleTokens": true,
 "textEncoderLr": 0.00005,
 "flipAugmentation": false,
 "trainTextEncoder": true
}</code></pre><h3 id="quality-tags-4-sierra">Quality tags 4 Sierra</h3><pre><code>### Masterpiece
Positive:
(masterpiece), (best quality), (ultra-detailed), ###{prompt}###, illustration, disheveled hair, detailed eyes, perfect composition, moist skin, intricate details, earrings, by wlop
Negative:
longbody, lowres, bad anatomy, bad hands, missing fingers, pubic hair, extra digit, fewer digits, cropped, worst quality, low quality
---------------------------

### Enhance
Negative:
(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4), (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark: name:1.2), (blur, blurry, grainy), morbid, ugly, asymmetrical, mutated, malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur:1.3), (3D, 3D Game, 3D Game Scene, 3D Character:1.1), (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3)

---------------------------

### Sharp
Positive:
cinematic still ###{prompt}###, emotional, harmonious, vignette, 4k epic detailed, shot on kodak, 35mm photo, sharp focus, high budget, cinemascope, moody, epic, gorgeous, film grain, grainy
Negative:
anime, cartoon, graphic, (blur, blurry, bokeh), text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured

---------------------------

### Photograph
Positive:
photograph ###{prompt}###, 50mm, cinematic 4k epic detailed photograph shot on kodak detailed cinematic hbo dark moody, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage
Negative:
Brad Pitt, bokeh, depth of field, blurry, cropped, regular face, saturated, contrast, deformed pupils, iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck

---------------------------

### Negative
Negative:
deformed, bad anatomy, disfigured, poorly drawn face, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, disconnected head, malformed hands, long neck, mutated hands and fingers, bad hands, missing fingers, cropped, worst quality, low quality, mutation, poorly drawn, huge calf, bad hands, fused hand, missing hand, disappearing arms, disappearing thigh, disappearing calf, disappearing legs, missing fingers, fused fingers, abnormal eye proportion, Abnormal hands, abnormal legs, abnormal feet, abnormal fingers, drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch

---------------------------

### Cinematic
Positive:
cinematic still ###{prompt}###, emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy
Negative:
anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured

---------------------------
</code></pre>

Files with SHA256: 2ebe2cc45a7e563f86b7ffebaa875621ff2dee37ed318f42bd9255ccaf573ff7