Upload 6 files

LowRA.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348071db544b7242c5edcb3306160d83bcde66395153c1daf38a575c5cefd66e
+size 75610142

LowRA.txt

@@ -0,0 +1,152 @@
+1. <lora:LowRA:0.6> redhead maid, mouth a bit opened, lightroom, pleasure look, maid white headdress, wet skin, detached collar, curly pixie haircut, small dark pantry, crowded cans shelfs, intricate, hdr, intricate details, hyperdetailed, cinematic
+Negative prompt: (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x768, Seed: 3515335635, Model: deliberate_v2, Steps: 26, Sampler: DPM++ 2M, CFG scale: 6, Model hash: 9aba26abdf, Hires steps: 8, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.33
+
+2. <lora:LowRA:0.7> a lion, epic, hdr, hyperdetailed, cinematic, muted colors, foggy bg
+Negative prompt: (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x768, Seed: 2799253289, Model: deliberate_v2, Steps: 22, Sampler: DPM++ 2M Karras, CFG scale: 6, Model hash: 9aba26abdf, Hires steps: 8, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.57
+
+3. <lora:LowRA:0.6> dark theme, rocks balancing
+Negative prompt: (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x768, Seed: 2757221325, Model: deliberate_v2, Steps: 25, Sampler: DPM++ 2M, CFG scale: 7, Model hash: 9aba26abdf, Hires steps: 8, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.55
+
+4. <lora:LowRA:0.6> dark, an old chieftainman, (astronaut outfit:1.2), feathers headdress, medium shot
+Negative prompt: (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x840, Seed: 711065367, Model: deliberate_v2, Steps: 22, Sampler: DPM++ 2M Karras, CFG scale: 7, Model hash: 9aba26abdf, Hires steps: 8, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.55
+
+5. <lora:LowRA:0.8> a tiny cabin, (tilt shift:1.2)
+Negative prompt: (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x768, Seed: 2490588977, Model: deliberate_v2, Steps: 22, Sampler: DPM++ 2M Karras, CFG scale: 7, Model hash: 9aba26abdf, Hires steps: 8, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.45
+
+6. <lora:LowRA:0.6> burger, dark theme
+Negative prompt: (deformed, distorted, disfigured), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x768, Seed: 3731322845, Model: deliberate_v2, Steps: 22, Sampler: DPM++ 2M Karras, CFG scale: 6, Model hash: 9aba26abdf, Hires steps: 8, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.36
+
+7. <lora:LowRA:0.7> a photo of a solarpunk living room with lots of flowers and plants, dark theme, evening
+Negative prompt: (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x768, Seed: 1421840128, Model: deliberate_v2, Steps: 22, Sampler: DPM++ 2M Karras, CFG scale: 7, Model hash: 9aba26abdf, Hires steps: 8, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.4
+
+8. <lora:LowRA:0.8> Маша making extreme selfie on skyscraper, bird's eye view, from above, night, smiling
+Negative prompt: (deformed, distorted, disfigured), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+Seed: 3135098381, Steps: 22, Sampler: DPM++ 2M Karras, CFG scale: 6
+
+9. <lora:LowRA:0.6> squirrel on a tree, hazelnut, cinematic, dark theme, rim light
+Negative prompt: (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x768, Seed: 921135546, Model: deliberate_v2, Steps: 24, Sampler: DPM++ 2M Karras, CFG scale: 6, Model hash: 9aba26abdf, Hires steps: 20, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.5
+
+10. <lora:LowRA:0.7> 250 gto, motion shot, dark theme, (hdr:1.2)
+Negative prompt: (deformed, distorted, disfigured), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x768, Seed: 1124475605, Model: deliberate_v2, Steps: 22, Sampler: DPM++ 2M Karras, CFG scale: 7, Model hash: 9aba26abdf, Hires steps: 8, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.4
+
+11. <lora:LowRA:0.8> hdr, a redhead woman climbing on mountains, frightened, closeup, intricate details, hyperdetailed, cinematic, dark shot, muted colors, film grainy, soothing tones, muted colors, technicolor, (muddy:0.6)
+Negative prompt: (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x768, Seed: 818146396, Model: deliberate_v2, Steps: 26, Sampler: DPM++ 2M Karras, CFG scale: 5, Model hash: 9aba26abdf, Hires steps: 8, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.42
+
+12. <lora:LowRA:0.6> hdr, oldman, closeup, (crowded newspapers store:1.2), hyperdetailed, cinematic, dark shot, muted colors, film grainy, soothing tones, muted colors
+Negative prompt: (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, dof
+ENSD: 31337, Size: 640x768, Seed: 2478123824, Model: deliberate_v2, Steps: 22, Sampler: DPM++ 2M Karras, CFG scale: 5, Model hash: 9aba26abdf, Hires steps: 8, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.36
+
+13. <lora:LowRA:0.6>, a portrait photo of a black girl, smiling, tattoo, blue dreads, (folk dress:1.3), Ukrainian short dress, pronounced feminine feature, insane details, intricate details, hyperdetailed, complex background, medieval tavern, indoors, muted colors
+Negative prompt: (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x768, Seed: 2966009108, Model: deliberate_v2, Steps: 26, Sampler: DPM++ 2M Karras, CFG scale: 5.5, Model hash: 9aba26abdf, Hires steps: 10, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.4
+
+14. <lora:LowRA:0.7> earth elemental in the form of a magical female, ominous
+Negative prompt: poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, mutated hands and fingers, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x768, Seed: 1086566181, Model: deliberate_v2, Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 6, Model hash: 9aba26abdf, Hires steps: 8, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.6
+
+15. <lora:LowRA:0.8> closeup, Scottish fold, sitting on a road, after rain, night, closeup, hyperdetailed, cinematic
+Negative prompt: b&w, (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x768, Seed: 1958668602, Model: deliberate_v2, Steps: 22, Sampler: Euler a, CFG scale: 6, Model hash: 9aba26abdf, Hires steps: 12, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.42
+
+16. <lora:LowRA:0.8> epic, маша друже makeup (друже:1.3), dark background
+Negative prompt: (deformed, distorted, disfigured), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+Seed: 1823710106, Steps: 22, Sampler: DPM++ 2M Karras, CFG scale: 6
+
+17. <lora:LowRA:0.6> creepy clown angry laughing, dark theme, soothing tones, muted colors, high contrast
+ENSD: 31337, Size: 640x768, Seed: 819557612, Model: deliberate_v2, Steps: 26, Sampler: DPM++ 2M Karras, CFG scale: 6, Model hash: 9aba26abdf, Hires steps: 8, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.36
+
+18. <lora:LowRA:0.7> drunk, creepy santa, muddy, crowded bottles bar, intricate details, hdr, intricate details, hyperdetailed, cinematic, dark shot, muted colors, film grainy, soothing tones, muted colors, technicolor
+Negative prompt: (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x768, Seed: 2035073191, Model: deliberate_v2, Steps: 26, Sampler: DPM++ 2M Karras, CFG scale: 5, Model hash: 9aba26abdf, Hires steps: 8, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.55
+
+19. <lora:LowRA:0.8> dark cinematic theme, woman, blue pixie haircut BREAK nun outfit, thick thighs, cross necklace, looking at viewer, medium shot, church altar background
+Negative prompt: poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x768, Seed: 2851286858, Model: deliberate_v2, Steps: 22, Sampler: DPM++ 2M Karras, CFG scale: 6, Model hash: 9aba26abdf, Hires steps: 8, Hires upscale: 2, Hires upscaler: 4x_NMKD-Siax_200k, Denoising strength: 0.46
+
+20. <lora:LowRA:0.7> a girl in the lake, (art by Jesper Ejsing:1.2)
+Negative prompt: (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation
+ENSD: 31337, Size: 640x768, Seed: 1076673168, Model: deliberate_v2, Steps: 22, Sampler: DPM++ 2M, CFG scale: 5.5, Model hash: 9aba26abdf, Hires steps: 8, Hires upscale: 2, Hires upscaler: 4x-AnimeSharp, Denoising strength: 0.42
+
+21. <lora:LowRA:0.8>, dark theme, absurdres, best quality, [1boy:1girl:0.2], tomboy, solo, very short hair, pixie cut, tan, (muscular:0.9), (large breasts:1), (medium breasts: 0.25), messy hair, night, aroused, lovestruck, looking at viewer, full-face blush, choker
+Negative prompt: lowres,  worst quality, low quality,  easynegative, bob cut, mole, tanlines
+ENSD: 31337, Size: 512x768, Seed: 1583200396, Model: aingexp_exp5, Steps: 30, Version: v1.2.1, Sampler: DPM++ SDE Karras, CFG scale: 10, Clip skip: 2, Model hash: d110e05043, Hires upscale: 2, Hires upscaler: None, Denoising strength: 0.5
+
+22. (masterpiece, top quality, best quality, official art, beautiful and aesthetic:1.2), , extreme detailed,colorful,highest detailed,(watercolour painting:1.3), optical mixing, playful patterns, lively texture, rich colors, unique visual effect, (beautiful detailed face and eyes), (masterpiece, top quality, official art, beautiful and aesthetic:1.2), (light painting), (long exposure:1.2), dynamic streaks, extreme detailed, in the style ofPhoenix, black paintings, shang dynasty, red and black, mecha anime, candid moments captured, slumped, draped, 1girl in black dress and looking his pet_Phoenix, Fire inflammation, best quality,A cute_red_Phoenix,pet,full body, full shot, fire surrounds the girl, The phoenix watched the girl fly beside the girl,  <lora:LowRa:0.5>
+Negative prompt: verybadimagenegative_v1.3, badhandv4, artist name, signture, extra fingers, fewer fingers, blurry, watermark, logo, nsfw, nipples, ((eyelashes)), ((speech bubble))
+Size: 640x960, Seed: 2110766038, Model: Ro+_bbMIXALICE_v10.ClearVAE, Steps: 30, Version: v1.2.1, Sampler: DPM++ 2M Karras, CFG scale: 7, Clip skip: 2, Model hash: 03cd9c4fbf, Hires steps: 20, Hires upscale: 2, Hires upscaler: R-ESRGAN 4x+, Denoising strength: 0.5
+
+23. masterpiece, best quality,
+1girl, ranni the witch, solo, blue skin,
+witch hat, large hat, sleeves past fingers,  long sleeves,
+full body, blue glow, silhouette, moon, starry sky,
+<lora:Ranni_the_Witch-07:0.7> <lora:LowRA_Dark:0.7>,
+Negative prompt: hand, nude, worst quality, low quality, badartist,
+1girl, ranni the witch, solo, blue skin,
+witch hat, large hat, sleeves past fingers,  long sleeves,
+full body, blue glow, silhouette, moon, starry sky,
+<lora:Ranni_the_Witch-07:0.7> <lora:LowRA_Dark:0.7>,
+Size: 576x768, Seed: 141991068, Model: toon_Cardology_v3, Steps: 25, Sampler: DPM++ 2M Karras, CFG scale: 7, Clip skip: 2, Model hash: 4af7f866a8, Hires steps: 15, Hires upscale: 2, Hires upscaler: 4x_Valar_v1, Denoising strength: 0.4
+
+24. grainy, extremely detailed, intricate detail, dynamic lighting,photorealistic, <lora:FilmG4:1>,filmg , natural lighting,   <lora:LowRA:1.2> ,low light,  <lora:m0nst3rfy3(0.5-1)M:0.8>,cat, slime, (red glowing eyes:1.2), :P, (fluffy,hairy,fluff,:1.3), (glowing stripes:1.1), raining,wet,dark theme, open mouth, lot of teeth, abyss, lurking in shadow,
+Negative prompt: (low quality, worst quality:1.4),  [bad-picture-chill-75v:Unspeakable-Horrors-Composition-4v:0.5],
+Size: 1024x1536, Seed: 3303057933, Model: revAnimated_v122FP32, model: control_v11f1e_sd15_tile [a371b31b], Steps: 100, weight: 1, Sampler: DPM adaptive, CFG mode: Half Cosine Up, CFG scale: 45, 'Overlap': 32, Clip skip: 2, "{'Method': 'Mixture of Diffusers', 'Upscaler': '4x_NMKD-Siax_200k', Mimic mode: Half Cosine Up, Model hash: 4199bcdd14, Mimic scale: 7, resize mode: Crop and Resize, control mode: ControlNet is more important, "preprocessor: tile_resample, pixel perfect: False, 'Scale factor': 2, starting/ending: (0, 1), 'Keep input size': True}", 'Tile batch size': 8, CFG scale minimum: 3, Denoising strength: 0.35, 'Latent tile width': 80, Mimic scale minimum: 3, preprocessor params: (64, 2.64, 64)", 'Latent tile height': 120, Threshold percentile: 95, Tiled Diffusion upscaler: 4x_NMKD-Siax_200k, Dynamic thresholding enabled: True, Tiled Diffusion scale factor: 2
+
+25. <lora:LowRA:1>, dark theme, absurdres, best quality, 1girl, tomboy, solo, very short hair, pixie cut, tan, (muscular:0.75), (large breasts:0.75), (medium breasts: 0.25), messy hair, night, aroused, lovestruck, looking at viewer, (full-face blush), eye focus
+Negative prompt: lowres,  worst quality, low quality,  easynegative, bob cut, mole,nipples, freckles,birthmark,  empty eyes, heterochromia, mature, (blurry:0.5), bags under eyes,
+ENSD: 31337, Size: 512x768, Seed: 3942014495, Model: chilloutworld_v15, Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 10, Clip skip: 2, Model hash: 7c889375ca, Hires upscale: 2, Hires upscaler: None, Denoising strength: 0.2
+
+26. <lora:LowRA:0.6>, dark theme, absurdres, best quality, androgynous,  <lora:Bao-000010:1>, red hair, long hair, red eyes, expressionless, suit, short sleeves, necktie, eye focus,
+Negative prompt: lowres,  worst quality, low quality,  easynegative
+ENSD: 31337, Size: 512x768, Seed: 3635832008, Model: seraphMix_v60, Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 10, Clip skip: 2, Model hash: 2429744b7d, Hires upscale: 2, Hires upscaler: None, Denoising strength: 0.3
+
+注意：
+Trigger Words：dark theme
+
+LowRA
+The Real Game Changer
+Now you can get as much low key as you need with just one LowRA
+
+Quick tips:
+Your start point (weight) is 0.6 ➜ <lora:LowRA:0.6>
+
+Looking for more darkness? Just add dark theme to your prompt
+
+The best weight range is about 0.6 ≈ 0.8
+
+Technical information:
+Dreambooth training (creation) models process is designed to turn each of your images into noise at each stage of training. This is done, so that later, during the image generation phase, Stable Diffusion could turn any random noise back into an image. The more you Train your model in Dreambooth (the more often you turn the same image into random noise), the easier it will be for Stable Diffusion to recreate the image you need from random noise (which Stable Diffusion creates itself). For example, If you turn 1 image into random noise 10 times (10 steps Dreambooth Training), then during generation, Stable Diffusion has 10 times more chance to recreate the image from noise. That's why we making thousands of training steps – to increase the probability of recreating an image.
+
+However, by turning any image into noise we get ≈45 to ≈55 percent of Brightness (HSB). Always. You can check this on python with numpy random or in Photoshop, just take a completely white square and a completely black square and then turn both into noise. Then Filter ➜ Blur ➜ Average. You will always get ≈45 to ≈55 percent of Brightness. That's why you always fail, when you trying to generate completely black square or completely white square. You just can't.
+
+LowRA solves this problem, when it embeds itself in the image generation process. At the beginning of the image generation process, LowRA gives you another noise, that allows you to get the image in the key you want. The higher the weight of LowRA, the more Stable Diffusion will be forced to use samples from LowRA. The samples used to train LowRA were strictly selected images that had an overall average Brightness of less than 25%. This made it possible to make the use of LowRA with less weight, so that when you use LowRA in parallel with other LoRAs, you don't get mess. So if you are using something else to get low key images in Stable Diffusion, you should forget the old techniques and just use LowRA.
+
+The careful selection of images in LowRA training proceeded as follows: a few thousand low key images were selected to begin with, each getting one noise pattern in Photoshop and a strict color palette for each individual subject. Warm and bright tones received no more than 25% of the space in the entire image. Next, each processed image was sent to img2img to create 10 similar generations. After that, a sample of the 10 images was tested for proper color reproduction in Photoshop. If the test passed, and the bright and warm tones did not exceed 25% of the Brightness, the image that was sampled was sent to dataset. If not, the image was simply deleted and the next image was taken. This rigorous and careful selection made it possible to obtain the ideal dataset for training. And now you can see the result of my work on this page.
+LowRA
+The Real Game Changer
+Now you can get as much low key as you need with just one LowRA
+
+Quick tips:
+Your start point (weight) is 0.6 ➜ <lora:LowRA:0.6>
+
+Looking for more darkness? Just add dark theme to your prompt
+
+The best weight range is about 0.6 ≈ 0.8
+
+Technical information:
+Dreambooth training (creation) models process is designed to turn each of your images into noise at each stage of training. This is done, so that later, during the image generation phase, Stable Diffusion could turn any random noise back into an image. The more you Train your model in Dreambooth (the more often you turn the same image into random noise), the easier it will be for Stable Diffusion to recreate the image you need from random noise (which Stable Diffusion creates itself). For example, If you turn 1 image into random noise 10 times (10 steps Dreambooth Training), then during generation, Stable Diffusion has 10 times more chance to recreate the image from noise. That's why we making thousands of training steps – to increase the probability of recreating an image.
+
+However, by turning any image into noise we get ≈45 to ≈55 percent of Brightness (HSB). Always. You can check this on python with numpy random or in Photoshop, just take a completely white square and a completely black square and then turn both into noise. Then Filter ➜ Blur ➜ Average. You will always get ≈45 to ≈55 percent of Brightness. That's why you always fail, when you trying to generate completely black square or completely white square. You just can't.
+
+LowRA solves this problem, when it embeds itself in the image generation process. At the beginning of the image generation process, LowRA gives you another noise, that allows you to get the image in the key you want. The higher the weight of LowRA, the more Stable Diffusion will be forced to use samples from LowRA. The samples used to train LowRA were strictly selected images that had an overall average Brightness of less than 25%. This made it possible to make the use of LowRA with less weight, so that when you use LowRA in parallel with other LoRAs, you don't get mess. So if you are using something else to get low key images in Stable Diffusion, you should forget the old techniques and just use LowRA.
+
+The careful selection of images in LowRA training proceeded as follows: a few thousand low key images were selected to begin with, each getting one noise pattern in Photoshop and a strict color palette for each individual subject. Warm and bright tones received no more than 25% of the space in the entire image. Next, each processed image was sent to img2img to create 10 similar generations. After that, a sample of the 10 images was tested for proper color reproduction in Photoshop. If the test passed, and the bright and warm tones did not exceed 25% of the Brightness, the image that was sampled was sent to dataset. If not, the image was simply deleted and the next image was taken. This rigorous and careful selection made it possible to obtain the ideal dataset for training. And now you can see the result of my work on this page.

qqq-breast_sucking-v1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa722e22f79c3a81aee5604b2186ecb473409ed03e9d51a2c8ffd3afdb9eb127
+size 37873705

qqq-breast_sucking-v1.txt

@@ -0,0 +1,61 @@
+1. masterpiece, best quality, 1girl, 1boy, breast sucking, lactation, breast grab, <lora:qqq-breast_sucking-v1:0.7>
+Negative prompt: (worst quality, low quality:1.4), EasyNegative, bad anatomy, bad hands, cropped, missing fingers, missing toes, too many toes, too many fingers, missing arms, long neck, Humpbacked, deformed, disfigured, poorly drawn face, distorted face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, out of focus, long body, monochrome, symbol, text, logo, door frame, window frame, mirror frame
+Size: 512x512, Seed: 4064419682, Model: AbyssOrangeMix2_hard, Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 7, Model hash: 0fc198c490
+
+2. masterpiece, best quality, 1girl, 1boy, breast sucking, <lora:qqq-breast_sucking-v1:0.7>
+Negative prompt: (worst quality, low quality:1.4), EasyNegative, bad anatomy, bad hands, cropped, missing fingers, missing toes, too many toes, too many fingers, missing arms, long neck, Humpbacked, deformed, disfigured, poorly drawn face, distorted face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, out of focus, long body, monochrome, symbol, text, logo, door frame, window frame, mirror frame
+Size: 512x512, Seed: 3844961354, Model: AbyssOrangeMix2_hard, Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 7, Model hash: 0fc198c490
+
+3. masterpiece, best quality, 1girl, 1boy, breast grab, breast sucking, lactation, <lora:qqq-breast_sucking-v1:0.8>, gotou1, gotou hitori, pink jacket, track jacket, bangs, hair between eyes, shaded face, <lora:gotou_hitori_v1:0.5>
+Negative prompt: (worst quality, low quality:1.4), EasyNegative, bad anatomy, bad hands, cropped, missing fingers, missing toes, too many toes, too many fingers, missing arms, long neck, Humpbacked, deformed, disfigured, poorly drawn face, distorted face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, out of focus, long body, monochrome, symbol, text, logo, door frame, window frame, mirror frame
+Size: 512x512, Seed: 4151755483, Model: AbyssOrangeMix2_hard, Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 7, Model hash: 0fc198c490
+
+4. masterpiece, best quality, 1girl, 1boy, breast sucking, <lora:qqq-breast_sucking-v1:0.8>, pekora1, <lora:pekora1-000009:0.5>
+Negative prompt: (worst quality, low quality:1.4), EasyNegative, bad anatomy, bad hands, cropped, missing fingers, missing toes, too many toes, too many fingers, missing arms, long neck, Humpbacked, deformed, disfigured, poorly drawn face, distorted face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, out of focus, long body, monochrome, symbol, text, logo, door frame, window frame, mirror frame
+Size: 512x512, Seed: 3427202398, Model: AbyssOrangeMix2_hard, Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 7, Model hash: 0fc198c490
+
+5. masterpiece, best quality, 1girl, 1boy, breast sucking, <lora:qqq-breast_sucking-v1:0.8>, yaemikodef, yaemikornd,<lora:yaemiko1-000008:0.4>
+Negative prompt: (worst quality, low quality:1.4), EasyNegative, bad anatomy, bad hands, cropped, missing fingers, missing toes, too many toes, too many fingers, missing arms, long neck, Humpbacked, deformed, disfigured, poorly drawn face, distorted face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, out of focus, long body, monochrome, symbol, text, logo, door frame, window frame, mirror frame
+Size: 512x512, Seed: 1515198797, Model: AbyssOrangeMix2_hard, Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 7, Model hash: 0fc198c490
+
+6. masterpiece, best quality, 1girl, 1boy, breast grab, breast sucking, lactation, <lora:qqq-breast_sucking-v1:0.8>, fischldef, fischlrnd, fischlein,<lora:fischl1-000008:0.5>
+Negative prompt: (worst quality, low quality:1.4), EasyNegative, bad anatomy, bad hands, cropped, missing fingers, missing toes, too many toes, too many fingers, missing arms, long neck, Humpbacked, deformed, disfigured, poorly drawn face, distorted face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, out of focus, long body, monochrome, symbol, text, logo, door frame, window frame, mirror frame
+Size: 512x512, Seed: 1155956098, Model: AbyssOrangeMix2_hard, Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 7, Model hash: 0fc198c490
+
+7. masterpiece, best quality, 1girl, 1boy, breast sucking, breast grab, <lora:qqq-breast_sucking-v1:0.9>
+Negative prompt: (worst quality, low quality:1.4), EasyNegative, bad anatomy, bad hands, cropped, missing fingers, missing toes, too many toes, too many fingers, missing arms, long neck, Humpbacked, deformed, disfigured, poorly drawn face, distorted face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, out of focus, long body, monochrome, symbol, text, logo, door frame, window frame, mirror frame
+Size: 512x512, Seed: 3712181400, Model: AbyssOrangeMix2_hard, Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 7, Model hash: 0fc198c490
+
+8. masterpiece, best quality, , 1girl, 1boy, (breast sucking:1.2), <lora:qqq-breast_sucking-v1:0.75> , crying, tear ,  <lora:yaeMikoGenshinImpact_v10:0.2>,yaemikodef     yaemikornd, pointy ears, long hair, heart ahoge, hair flower,white headwear,blue bow, blue bowtie, official wear, blue hair, yellow eyes,
+Negative prompt: (worst quality, low quality:1.4), EasyNegative, bad anatomy, bad hands, cropped, missing fingers, missing toes, too many toes, too many fingers, missing arms, long neck, Humpbacked, deformed, disfigured, poorly drawn face, distorted face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, out of focus, long body, monochrome, symbol, text, logo, door frame, window frame, mirror frame
+ENSD: 31337, Size: 512x512, Seed: 2842538376, Model: AbyssOrangeMix2_AbyssOrangeMix2_hard, Steps: 25, Sampler: DDIM, CFG scale: 7, Model hash: 0fc198c490, Hires upscale: 2, AddNet Enabled: True, AddNet Model 1: yukihanaLamyHololive_v10(9d050794b69a), Hires upscaler: R-ESRGAN 4x+ Anime6B, AddNet Module 1: LoRA, ControlNet Model: control_v11p_sd15_openpose [cab727d4], AddNet Weight A 1: 0.1, AddNet Weight B 1: 0.1, ControlNet Weight: 1, ControlNet Enabled: True, Denoising strength: 0.1, ControlNet Ending Step: 1, ControlNet Resize Mode: Crop and Resize, ControlNet Control Mode: Balanced, ControlNet Preprocessor: none, ControlNet Pixel Perfect: False, ControlNet Starting Step: 0, ControlNet Preprocessor Parameters: "(512, 64, 64)"
+
+9. masterpiece, best quality, breast sucking,  breast grab, (1girl, huge breasts, lactation, mature female, milf, black hair, blunt bangs, ponytail, dark skin, pointy ears:1.0), blush, heavy breathing, heart, (1boy, long hair),  <lora:qqq-breast_sucking-v1:0.65>
+Negative prompt: EasyNegative, drawn by bad-artist, (bad_prompt:0.8), (artist name, signature, watermark:1.4), (ugly:1.2), (worst quality, poor details:1.4), bad-hands-5, blurry, penis,
+ENSD: 31337, Size: 512x768, Seed: 2036672838, Model: A1_DarkSun_t1_baked_klf8, Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 7, Clip skip: 2, Model hash: 9a4d193dfc, Hires upscale: 2, Hires upscaler: 4x-UltraSharp, Denoising strength: 0.35
+
+说明：
+
+Trigger Words：breast sucking
+
+Here is the Lora for breasts sucking!
+
+The trigger words is breast sucking, (optional: lactation, breast grab)
+
+The suggested weight is 0.7 - 0.8
+
+Hope you enjoy my work!
+
+You are welcome to browser my other works if you are interested!
+
+#
+
+New Announcement (19th April)
+
+Hello my followers. I am sorry that I bring a bad news to you today. The update frequency of Lora may be dropped dramatically or even be stopped for some reason. You can still leave your request for free (discord: qqqw123#4777) but I am not 100% sure I will make it. Thanks for your support and appreciation!
+
+#
+
+You are also welcome to leave your request for free and I will try to make it into a Lora if it is possible.
+
+If you appreciate my works, you can support me via donation on ko-fi.com/dpp12