Model
Trends
.ai
Model
Trends
.ai
die besten Open-Source-KI-Modelle
Lokal ausführen
ghouls.safetensors
36 MB · SafeTensor
Downloads werden von Civitai bereitgestellt. Manche Ersteller verlangen zuerst eine Anmeldung bei Civitai.
AD
Auf Graydient installieren / ausführen
Mitgliedschaft erforderlich
<ghoul>
Über dieses Modell
STABLE DIFFUSION 1.5 · LoRAs
Erstellt von
Eggbena
auf Civitai
Designed by Community Member Eggs-Benadryl. This lora is designed to generate sentient ghouls from the Fallout series, a popular video game franchise. It can create both animated and realistic models of these irradiated humanoids, with various levels of decay and mutation. You can adjust the weight parameter from 1 to 1.5 to control the effects. To avoid unwanted features such as glowing eyes or zombie-like effects, you can use the negative prompt option to exclude them from the generation process. This lora is ideal for fans of the Fallout series who want to create their own ghoul characters or scenarios.
Notizen des Erstellers
never tested, will update high expectations doesn't look promising now, trained on zero feral and no body shots far as I know but it's coming out far more zombie than I expected It looks like good results are possible. For the good examples, man, portrait were the only prompts, Rev animated was used with 2 clipskip. If you're getting too many zombie like renders, try putting that into the negative. Prompting in clothing helps and prompts about the eyes help them appear less glowing or milky etc.
Triggerwörter
ghoul
697 Downloads · 71 Likes auf Civitai
SHA256
8B3E08782FE08B38D07680A7A747CA70CE742394F0556F347DC3FF1DF8A9C422
ModelTrends.ai-Modell-ID
#6198
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
DPM++ 2M Karras
Schritte
50
Guidance
7
Seed
1832046067
Größe
512x512
Clip skip
2
Verwendetes Gewicht
1.7
Prompt
ghoul, man, male focus, solo, looking at viewer, leather armor, top hat, proportional eyes, (realistic:1.5), photorealistic, hyper-realistic, extremely detailed, hyper-detailed, soft lighting, detailed background, extreme detail background, sharp details, ((full body))
Negativer Prompt
zombie, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, watermark, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face, blurry, draft, grainy, cowboy hat
Einstellungen
Sampler
DPM++ 2M
Schritte
30
Guidance
8
Seed
3127887161
Größe
624x800
Prompt
full body <lora:ghouls:1> ghoul, <lora:The_Silver_Shroud_Fallout:1> silvershroud, black hat, gray scarf, long black coat, black gloves, black pants, black shoes, best quality, masterpiece, detailed, 8K, uhd, (extremely detailed CG unity 8k wallpaper),(masterpiece), (best quality), (ultra-detailed), (best illustration), detailed face, skin pores, detailed skin, detailed eyes, high quality eyes, good quality hands, high resolution, OverallDetail,
Negativer Prompt
(worst quality, low quality:1.2), text, bad quality, watermark, BadDream, bhands-neg, FastNegativeV2, UnrealisticDream
KI-Modelle für Bild-, Video- und Texterzeugung
ghoul ist ein LoRA für die Familie Stable Diffusion 1.5 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 1.5-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