Model
Trends
.ai
Model
Trends
.ai
die besten Open-Source-KI-Modelle
Lokal ausführen
AnimaLORA_r3gd1c_3840-rank32_alpha32_rank32_bf16.safetensors
88 MB · SafeTensor
Downloads werden von Civitai bereitgestellt. Manche Ersteller verlangen zuerst eine Anmeldung bei Civitai.
AD
Auf Graydient installieren / ausführen
Mitgliedschaft erforderlich
<regdic2p1-anima>
Über dieses Modell
ANIMA · LoRAs
Erstellt von
zeuss194
auf Civitai
by zeuss194 - Regdic Anima V2.1
Notizen des Erstellers
Lora that mimic the style of Regdic or Regudeku Trained locally with my own tool, ComfyUI-AnimaTrainer () - About V2.1 [Same as previous model in term of dataset, with about 25% more training steps, and a different trigger word that won’t trigger the pretrained style from base model] Trigger word is r3gd1c for V2.1 The V2.1 is kind of experimental for me and the goal is to test model behavior and interaction between lora and the base training. It is also to learn how prompting weight and placement inside the prompt does affect the output. Long story short and random information about prompting: - you can call upon base model knowledge with “” - you can call upon lora V2.1 knowledge with “r3gd1c” You can stack both but result can be messy and need weight tuning The Lora is better at giving the recent style from the artist than the base model Moderate weighting on both Lora and trigger word is surprisingly effective and can help a lot, example (r3gd1c:1.2) with lora at 1.1 Base model output With lora at 1.0 and r3gd1c with lora at 1.2 and (r3gd1c:1.3) - About V2 [Anima base V1, new training parameters, new images, new caption and tags, trained with regularization] Regularization lengthen the training but allow great flexibility and improve promptability in case of lora stack or mixed style. Weight from 0.4 to 1.8, you must use trigger word for effect, you can start low like 0.5 or 0.6 as the base model already know the artist, the lora act as a reinforcement Example on base model + lora @ 0.5 + lora ! About V1B Weight from 0.8 to 1.0 , mostly character focus , no trigger I had hard time to decide which Lora stepping/epoch I should publish, I run into lot of small issues that force me to retrain it 3 times and to redo dataset. And some inconsistency in Inference were annoying as well. The lora supplied here is the most predictable for the moment imho. I will revisit it later once I'll have built a better datasets and better training parameters. (check V2 is out) For the time being, enjoy ! o7
Triggerwörter
r3gd1c
104 Downloads · 5 Likes auf Civitai
SHA256
375F382F6F0194B625A68D9882DE7EF967E1E083E2008807E8C2FFF400162883
ModelTrends.ai-Modell-ID
#25624
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
er_sde
Schritte
42
Guidance
3
Größe
1536x2048
Prompt
masterpiece, score_8_up, score_7_up, (r3gd1c:1.3), best quality, A boy with short dark hair and fair skin stands beside a girl with light purple shoulder-length hair tied into a side ponytail, both sheltered under a large red umbrella against a downpour. The boy wears a white collared shirt beneath a dark green V-neck sweater vest, paired with black trousers; he holds a small gray bag in his right hand and gazes slightly upward with a calm expression. His companion, the girl, is dressed in a crisp white short-sleeved blouse adorned with a navy blue bow at the collar, a pleated dark navy skirt that ends mid-thigh, and black ankle boots with buckles slung over one shoulder. She clutches the umbrella’s curved red handle with both hands, her wide brown eyes sparkling with delight as she smiles softly toward the viewer. Rain streaks vertically across the scene, blurring background elements — faint outlines of buildings, utility poles, and wet pavement reflecting ambient daylight suggest an urban street during daytime. A black backpack rests on the girl’s left shoulder, its straps visible over her uniform. The composition centers the pair closely together, emphasizing intimacy amid the storm, while soft shading and layered colors lend depth to their clothing textures and the glistening rain-slicked environment around them.
Negativer Prompt
worst quality, low quality, score_1, score_2, score_3, bad quality, worst quality, worst detail, censored, extra limb, 3d, realistic, yaoi, mosaic censoring, bar censor, light censor, futanari, futa, multiple girls, crowd, military uniform, epaulettes, belt, belt buckle, uniform shorts, black pantyhose, boots,
Einstellungen
Sampler
er_sde
Schritte
20
Guidance
2
Seed
743346950
Größe
832x1216
Verwendetes Gewicht
1
Prompt
masterpiece, best quality, masterpiece, best quality, perfect quality, 1girl, karazorel, blonde hair, blue eyes, short hair, scrunchie, blonde hair, blue eyes, earrings, midriff, jeans, hand on hip,hand in hairs,upper body shot, hairband, earrings, white shirt, (open shirt), smug, taut shirt, medium breasts, 1girl, supergirl, blonde hair, blue eyes, short hair, my adventures with superman, simple background, white background, r3gd1c ,
Negativer Prompt
worst quality, low quality, bad, artistic error, worst aesthetic, jpeg artifacts, bad hands, mutated hands, extra digits, ugly, signature, watermark, fewer digits, extra digits, mutated hands, bad hands, extra ears, detached tail, loli, aged down, child, shota, extra pupil, giantess, giant, extra navel, anthro, furry female, hand mark, injury, animal nose,
Einstellungen
Sampler
er_sde
Schritte
46
Guidance
4.5
Seed
1773618480
Größe
832x1216
Verwendetes Gewicht
1.35
Prompt
masterpiece, (r3gd1c:1.3), score_8_up, score_7_up, monogatari \(series\), anime coloring, anime screenshot, Long hair, red hair, Horns, horn Ornament, yellow eyes, pointy ears, 1girl, solo, looking at viewer, casual outfit, earthy tones, natural materials, jungle outfit, wilderness attire, tropical casual, adventure outfit, practical jungle, tarzan aesthetic, jane outfit, masterpiece, best quality, very awa, absurdres, very aesthetic, ultra-detailed
Negativer Prompt
worst quality, low quality, score_1, score_2, score_3, bad quality, worst quality, worst detail, sketch, censored, watermark, english text, 3d, realistic, shota, loli, yuri, yaoi, mosaic censoring, bar censor, light censor, futanari, futa, multiple girls, crowd, people,
Einstellungen
Sampler
er_sde
Schritte
42
Guidance
3
Größe
1536x2048
Prompt
masterpiece, score_8_up, score_7_up, (r3gd1c:1.3), masterpiece, best quality, highres, 1girl, solo, confident, messy hair, short, casual, hoodie, jeans, high angle, cowboy shot, standing, looking at viewer, ruin, abandoned, golden light, warm, anime, style, medium breasts,
Negativer Prompt
worst quality, low quality, score_1, score_2, score_3, bad quality, worst quality, worst detail, sketch, censored, extra limb, 3d, realistic, shota, loli, yuri, yaoi, mosaic censoring, bar censor, light censor, futanari, futa, multiple girls, crowd, people, military uniform, epaulettes, belt, belt buckle, uniform shorts, black pantyhose, boots,
Einstellungen
Sampler
er_sde
Schritte
40
Guidance
4.8
Größe
896x1088
Prompt
masterpiece, score_8_up, score_7_up, (r3gd1c:1.3), masterpiece, highres, best quality, 1girl, young woman, from above, pink eyes, tank top, shorts, from above, looking up, cavern, rocky, shallow depth, focused
Negativer Prompt
worst quality, low quality, score_1, score_2, score_3, bad quality, worst quality, worst detail, sketch, censored, extra limb, 3d, realistic, shota, loli, yuri, yaoi, mosaic censoring, bar censor, light censor, futanari, futa, multiple girls, crowd, people, military uniform, epaulettes, belt, belt buckle, uniform shorts, black pantyhose, boots,
KI-Modelle für Bild-, Video- und Texterzeugung
regdic2p1 anima ist ein LoRA für die Familie Anima und wird auf ModelTrends.ai gelistet, einem reinen Lesekatalog für Open-Source-KI-Modelle für Bild, Video und Text. Vergleiche es mit anderen Anima-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