Model
Trends
.ai
Model
Trends
.ai
die besten Open-Source-KI-Modelle
Lokal ausführen
vermilion_v31ChenkinnoobV02.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Downloads werden von Civitai bereitgestellt. Manche Ersteller verlangen zuerst eine Anmeldung bei Civitai.
AD
Auf Graydient installieren / ausführen
Mitgliedschaft erforderlich
<vermilion-3p1-xl>
Über dieses Modell
STABLE DIFFUSION XL 1.0 · Basismodelle
Erstellt von
Manityro
auf Civitai
by Manityro - Vermilion V3.1 ChenkinNoob V0.2
Notizen des Erstellers
If the images are too dark for your taste put "dark theme" into the Negative prompt. V3-ChenkinNoob: New rebake of all styles used and then merged on the new since it has helped make the gens a lot cleaner. Note all previous illustrious-0.1 and NoobAi loras work perfectly fine from what I have tested on ChenkinNoob. If you are using Reforge WebUi turning on EPS scaling can help improve gens further, I personally also use FreeU for the samples above. Gen settings I use are the same as previous versions. Fixed some of the quirks from V2.2 but please do share if you find anything I may I have missed. My Generation Settings for V2-3: - Sampler: Euler A AYS - Sampling Steps: 24 - Upscaler settings: - or - 1.5x - 2.0x Upscale - 10 Hires steps - Denoise 0.1-0.6 (Use lower denoise on higher Upscale) - Suggested Dimensions: 832x1216, 1216x832, or 1024x1024 - CFG Scale: 4-6 - along with - Inpaint Denoise: 0.2-0.5 - Use Separate width/height: - 1024x1024 - Inpaint mask blur: 24 - Inpaint only masked padding, pixels: 48 - Positive prompt base: - masterpiece, best quality, - Negative prompt base: - worst quality, low quality, bad anatomy, watermark V2.2: Extra re-merge using as base and removed some of the other checkpoints, now its just used as an extra mixed on The finger issues from V2.1 have been much reduced and somehow after lots of mixing it came out even cleaner so I hope you all enjoy. Worst case use fewer digits in the negative for more finger stability. V2.1: Remerge using as base and changed the other ckpts to , and on Was noticing various finger and hand issues with blur and artifacts that bugged me so I went and tried to fix it. Should be a lot better and cleaner now but if anything is consistently odd please let me know. If you have some issues with fingers add (fewer digits, 3 fingers:1.3) to the negative and it should help until I update the model later. V2: Updated merge using as base with some and on Goal of V2 was to use Anzhc's new VAE which is baked into the model, I suggest to use this VAE or none as its baked in. Otherwise I wanted to make the mix cleaner and sharper with much better dark gens. Use: Dark, dark theme, darkness for general dark gens or night, dim lighting for light specific darkness. There are some mild quirks, if animal ears fail make sure to add animal ears tag to stabilize it. Sometime extra people leak into gens if you forget solo. Will fix most of the issues with a V3 but I need to remake and find more styles before I can do that. V1: Based on and so please visit that page for a rundown of prompts, tags and other baked in features. This model is a merge of Styles I baked and then mixed on . My Generation Settings for V1: - Sampler: Euler A AYS - Sampling Steps: 24 - Upscaler settings: - or - 1.5x - 2.0x Upscale - 10 Hires steps - Denoise 0.1-0.6 (Use lower denoise on higher Upscale) - Suggested Dimensions: 832x1216, 1216x832, or 1024x1024 - CFG Scale: 4-6 - along with - Inpaint Denoise: 0.2-0.5 - Use Seperate width/height: - 1024x1024 - Inpaint mask blur: 24 - Inpaint only masked padding, pixels: 48 - Positive prompt base: - masterpiece, best quality, - Negative prompt base: - worst quality, low quality, bad anatomy, watermark Important note: Baked in characters for illustrious/NoobAi are often burnt so you may need to reduce weight so it doesn't make the ckpt look strange. New merge to tickle a different craving I was having, spent some time improving my ability to train styles and used that to make the styles I merged into this model. I hope you all enjoy. Check out the samples above for inspiration and/or ideas.
460 Downloads · 80 Likes auf Civitai
SHA256
9581DC225953B6A27498CD908F5CF3C9210F484EC95D232388120C5CEE098CCA
ModelTrends.ai-Modell-ID
#20963
Inhalt melden
Beispielbilder
Prompts und Einstellungen, geteilt von den Leuten, die diese Bilder auf Civitai erstellt haben. Wähle ein Bild, um zu sehen, wie es entstanden ist.
Einstellungen
Sampler
Euler a
Schritte
24
Guidance
6
Seed
1890095564
Größe
1248x1824
Prompt
newest, solo, 1girl, open mouth, looking at viewer, walking, holding magnifying glass, short hair, brown hair, hair between eyes, crossed bangs, deerstalker, brown eyes, earrings, brown coat, long coat, open coat, long sleeves, white shirt, collared shirt, shirt tucked in, black necktie, black pants, brown belt, outdoors, night, star \(sky\), cobblestone, lamppost, building <segment:yolo-Anzhc Face seg 640 v4 y11n.pt,0.5,0.5//cid=11>
Negativer Prompt
worst quality, low quality, jpeg artifacts, multiple views, comic, text, dual wielding
Einstellungen
Sampler
Euler a
Schritte
24
Guidance
6
Seed
1095428592
Größe
1248x1824
Prompt
newest, solo, 1girl, sweat, expressionless, looking at phone, sitting, park bench, holding phone, arm support, short hair, black hair, bob cut, purple eyes, track suit, red jacket, track jacket, long sleeves, red pants, outdoors, day, tree <segment:yolo-Anzhc Face seg 640 v4 y11n.pt,0.5,0.5//cid=11>
Negativer Prompt
worst quality, low quality, jpeg artifacts, multiple views, comic, text
Einstellungen
Sampler
Euler a
Schritte
24
Guidance
6
Seed
12505584
Größe
1248x1824
Prompt
newest, solo, 1girl, wsmistral, scar across eye, sweat, expressionless, looking at phone, sitting, park bench, arm support, holding phone, smartphone, long hair, white hair, side ponytail, tiara, blue eyes, track suit, red jacket, track jacket, long sleeves, red pants, outdoors, day, tree <segment:yolo-Anzhc Face seg 640 v4 y11n.pt,0.5,0.5//cid=11>
Negativer Prompt
worst quality, low quality, jpeg artifacts, multiple views, comic, text
Einstellungen
Sampler
Euler a
Schritte
24
Guidance
5
Seed
2353767264
Größe
832x1216
Prompt
masterpiece, best quality, 1girl, smile, open mouth, teeth, looking at viewer, standing, hand on own chest, outstretched arm, reaching towards viewer, spotlight, (hatsune miku, vocaloid:0.7), long hair, aqua hair, hair between eyes, twintails, hair ornament, headset, aqua eyes, grey shirt, collared shirt, sleeveless shirt, untucked shirt, aqua necktie, black sleeves, detached sleeves, black skirt, pleated skirt, black thighhighs, cowboy shot,
Negativer Prompt
worst quality, low quality, bad anatomy, watermark, mole,
Einstellungen
Sampler
Euler a
Schritte
24
Guidance
5
Seed
2577801387
Größe
832x1216
Prompt
masterpiece, best quality, 1girl, <lora:doro_xypher_naixl_v2:1>, doroxyp, :3, no pupils, no humans, pokemon \(creature\), blush, chibi, pink hair, purple eyes, hair bow, white bow, hair ribbon, purple ribbon, single side bun, hair between eyes, sidelocks, hair intakes, bangs, white skin, running towards viewer, angry, motion lines, speed lines, charging forward, running, standing, leaning forward,
Negativer Prompt
worst quality, low quality, bad anatomy, watermark, mole, all fours
Einstellungen
Sampler
Euler a
Schritte
24
Guidance
6
Seed
743726179
Größe
1248x1824
Prompt
newest, solo, 1girl, sweat, smile, :q, looking at viewer, standing, selfie, outstretched arm, holding water bottle, very long hair, aqua hair, hair between eyes, twintails, hair ornament, aqua eyes, one eye closed, track suit, red jacket, track jacket, long sleeves, red pants, outdoors, day, park, path <segment:yolo-Anzhc Face seg 640 v4 y11n.pt,0.5,0.5//cid=11>
Negativer Prompt
worst quality, low quality, jpeg artifacts, multiple views, comic, text
Einstellungen
Sampler
Euler a
Schritte
24
Guidance
6
Seed
1157186065
Größe
1248x1824
Prompt
newest, solo, 1girl, smile, looking at viewer, standing, leaning forward, hands on own thighs, very long hair, red hair, ponytail, aviator sunglasses, eyewear on head, green eyes, white shirt, off-shoulder shirt, short sleeves, bra strap, black bra, blue shorts, denim shorts, cutoffs, outdoors, day, urban, city street <segment:yolo-Anzhc Face seg 640 v4 y11n.pt,0.5,0.5//cid=11>
Negativer Prompt
worst quality, low quality, jpeg artifacts, multiple views, comic, text
Einstellungen
Sampler
Euler a
Schritte
24
Guidance
5
Seed
3301040823
Größe
832x1216
Prompt
masterpiece, best quality, 1girl, dark orange eyes, red hair, (orange colored inner hair:1.1), (glowing inner hair:0.7), long hair, blunt bangs, fringe trim, low-tied long hair, large breasts, hair flaps, toned, white armor, spacesuit, white pauldrons, high collar, white breastplate, orange glow, glistening, sparkle, orange aura, (black hole:0.8), looking at viewer, lips, smile, head tilt, (smirk:1.2), smile, parted lips, (head back:0.8), red space, starry background, star \(sky\), (orange nebula, orange galaxy:1.2), science fiction armor, upper body, portrait, close-up, (abstract, abstract background:1.5), (from side:0.8), chromatic aberration, dark theme, dark, darkness, backlighting,
Negativer Prompt
worst quality, low quality, bad anatomy, watermark, mole,
KI-Modelle für Bild-, Video- und Texterzeugung
vermilion 3p1 xl ist ein Basismodell für die Familie Stable Diffusion XL 1.0 und wird auf ModelTrends.ai gelistet, einem reinen Lesekatalog für Open-Source-KI-Modelle für Bild, Video und Text. Vergleiche es mit anderen Stable Diffusion XL 1.0-Modellen, prüfe den Hitzewert, um den Trend zu sehen, und öffne es auf PirateDiffusion oder BitVector, um es auszuprobieren.
Nach Modellfamilie stöbern
Alle Modelle ansehen