Model
Trends
.ai
Model
Trends
.ai
los mejores modelos de IA de código abierto
Ejecutar en local
goddessOfRealism_gorPONYV10.safetensors
6.46 GB · SafeTensor · fp16 · full
Las descargas las sirve Civitai. Algunos creadores piden iniciar sesión en Civitai primero.
AD
<goddess-realismpony1-xl>
Sobre este modelo
STABLE DIFFUSION XL 1.0 · Modelos base
Creado por
Oppkllll
en Civitai
GODDESS of Realism V1 - GoR Pony by Opkill is a realistic pony model. Note that a newer version of this model, beta 2, is also available on our platform. 35-45 steps with a max guidance of 10 is recommended. DPM2M Karras sampler is recommended to bring out more details.
Notas del creador
GoR_v6ILXL+VAE SETTINGS: DPM++ SDE Karras, DPM++ 2S a Uniform EULER A Karras clip skip 2 Steps +/-30 GFC+/-7 Well, I committed this version. Take into consideration that trying to make this model realistic may have messed with the base illustrous a bit. The effects may be surprising ;) SDE can sometimes burn through but for that Euler A is finally useful. You can also test clipskip 1, but for me it is too “smooth” PS: And one more thing, if you see that I used your original prompt, please link the post in the comment under the image. Sometimes I'm surfing the civitai gallery and testing the prompts on my models and then just can't figure out what's from where -GoR_PONY_v5ilustros_H+VAE! This is experiment, it is Pony but with a liitle of Illustrious, lets say it is beta test SETTINGS: DPM++ SDE Exponential clip skip 2 CFG: 4,5 to 6,5 Use negative prompt not only pony ones Check my pics for settings Please upload your work, it will allow me to improve the model. I myself don't have much time lately to do thorough tests -GODDESS of Realism - GoR_PONY_v4photo+VAE!b Sampling method: DPM++ SDE Karras Sampling steps: 25 up+ CFG Scale: 6.5 Width: 832 Height: 1216 Clip skip 2 For distance shot recomended ADetailer for better faces Others: I don't quite know if it makes a difference but it seems to me that it improves the quality of the images Clip skip SDXL on Emphasis mode No norm Enable T5 The models used initially before my own training to create base GoR Pony were definitely Pony Realism and probably CyberRealistic Pony, DucHaiten-Pony-Real, Zonkey - Realism, DAMN! and in v1 Everclear PNY. I don't remember all exactly because I had probably all the realistic PONY models on disk. Thank you to all the creators. GoR pony v3 The basic idea is to create the most versatile model, from nice views to NSFW and from robots and monsters to fury. V3 derives from v2art but managed to get crisp colors like in beta or 1. While the quality of textures is 100x better. I noticed that this version likes tags from sd1.5 such as HD, cinematic etc.... Also, the negative long shuttles have a very big impact but be careful. Beware of too big values especially for tags related to lighting (1.3), (1.5) and too much (((()))) etc. The model has a lot to be perfect, I'm still not satisfied with the face and hands in the distance shots. If anyone finds some lore or embedding that improves this please share in the comments. Enjoy V2art_fix+VAE! All DPM++ works good, for scifi/art 2m SDE and 2m SDE Heun for human realism best DPM++ 2S a and DPM++ 3M SDE, DPM++ SDE Karras CFG scale 8-9 Steps 30up VAE baked in clipskip 1 wuler and euler a not recomended Edit : The size of the model is a consequence of using the "checkpoint model mixer." I checked with other settings and it just comes out that way. As you can see from the added images it works correctly Edit 2: LORAs trained on Pony Diffusion and Pony Realism works good. On Everclear not. I turned on "Lora/Networks: use old method" in a1111 settings GoR_PONY_V2art: I added some custom lora to change mood of images It is very sensitive model so don't go to high with ((()))) and (1.4) All DPM++ works good, I prefer 2M karras GFC from 5 to 7 Steps 30up VAE standard sdxl clipskip 1 If you see others problems sher it so I can fix them in next version tested in automatic1111 GoR PONY_v1 GFC works up to 10 DPM++ 2M karras = fast DPM++ SDE karras = quality 3MSDE, Euler, Euler a = works fine to Steps= 30-45 VAE standard sdxl Be careful with adding too many tags like: photorealistic, photography, bokeh etc.... Sometimes their excess causes errors GoR PONY_beta DPM++ 2M SDE karras-30steps for simple image and 40-50 for more complicated, for more info check posted images dataset and compare of all samplers GFC: 2 for realistic up to 7 to get more vibrant Pony "scores" and tags for positive and negative SD:1.5 description below This is a mix of very many models from this site. The main goal was to create more artistic photographs in different styles. Prompt; photo type > angle > subject >subject details > background > quality tags (not necessarily) > style (not necessarily) samplers best with DPM++ SDE Karras steps 25+ gfc 7 hires fix as you like ( I prefer foolhardy) Clip Skip 1 It dislikes "full body shot" use full shot and others Negative prompt dangerdonkey, kkw-new-neg-v1.6 ,(low water quality:1.45), low particles efects, ( 3d render, anime, draw, cartoon, grotesque),( over saturated:1.1), jpeg artifacts, out of frame, (((watermark, signature))), lowres, (low quality skin:1.1), , error, compressed, 000, dolly skin, (plastic doll), barbie, (lolicon, loli:1.2), childlike, 000, bad anatomy, bad hands, mutated hand, missing fingers, fused fingers, extra fingers, extra arms, long neck, amputation, (poor quality feet:1.0), wrong number of feet, blending objects, extra digit, fewer digits, cropped, out of frame, error, extra limbs, mutation, bad proportions, cropped head, malformed limbs, mutated hands, mutated feet, missing limbs, cropped, deformed, ugly, mutilated, disfigured, face cut, head cut, legs cut, poorly drawn face, animals, nsfw,
5,609 descargas · 473 me gusta en Civitai
SHA256
41F3B63DC15410BC8D7CB88B3E97D85A8F7333682E00CA98BAB3651C32DAA923
ID de modelo de ModelTrends.ai
#10606
Denunciar contenido
Renders de ejemplo
Prompts y ajustes compartidos por quienes hicieron estos renders en Civitai. Elige un render para ver cómo se hizo.
Ajustes
Pasos
20
Guidance
4
Semilla
219099235
Tamaño
480x672
Prompt
The scene opens with an extreme close-up of a grotesque, green, flesh-eating plant. Its surface is slick and wet, pulsing slightly as if breathing, its skin covered in veiny textures. Rows of razor-sharp, jagged teeth glisten with slime inside its gaping maw. The plant snaps its jaws violently toward the camera several times, each chomp accompanied by a wet, bone-crunching sound. Tiny strands of saliva stretch and snap with every bite, flicking toward the lens. Suddenly, the plant lets out a chilling, guttural scream — a high-pitched, unnatural screech — as it lunges directly at the viewer. In the final second, the forest behind her seems to twist and darken, shadowy figures appearing between the trees — and just as the screen flickers, she lunges forward, mouth gaping open in a silent, monstrous scream — then everything cuts abruptly to black.
Ajustes
Sampler
DPM++ 2M
Pasos
30
Guidance
2.5
Semilla
1473784334
Tamaño
832x1216
Prompt
score_9, score_8_up, score_7_up, portret photo of mature woman from brasil, sitting in restaurant, sun set
Prompt negativo
core_6, score_5, score_4, BeyondSDXLv3, , (3d render, anime face, draw, cartoon, manga face, grotesque), (((watermark, logo, signature))), lowres, (low quality skin:1.1), error, compressed, (plastic doll),(lolicon, loli:1.2), childlike, bad anatomy, ((bad hands)), mutated hand, (fused fingers), extra fingers, (poor quality feet:1.0), ((bad legs)), wrong number of feet, fewer digits, mutation, bad proportions, mutated hands, mutated feet, deformed, mutilated, ((disfigured)), bad art, ugly, tiling
Ajustes
Sampler
DPM++ 2M SDE Heun
Pasos
25
Guidance
7
Semilla
2875090498
Tamaño
832x1216
Prompt
score_9, score_8_up, score_7_up, very tall alien female, growths on the head, she wearing orange futuristic mechanic's jumpsuit with lots of pockets and straps, long thin arms, long thin legs, alien anatomy, knees turned back, twisted joints, coloured skin, narrow chest, alien landscape, alien planet, broken alien aircraft on the ground, green sky
Prompt negativo
score_1, score_2, score_3,
Ajustes
Sampler
DPM++ SDE Karras
Pasos
120
Guidance
10
Semilla
213371679
Tamaño
768x1024
Prompt
score_9, score_8_up, score_7_up, (realistic:1.2), volumetric light, dark shadows, masterpiece, BREAK, girl, solo, anthro, furry, feline, petite, skinny, <lora:sawyer-cdd:.5> sawyer_cdd, detailed fluffy fur, white body, white skin, white fur, long fluffy tail, sexy, wide hips, slim waist, (thin_waist:2), hand paws, <lora:Leg Length Slider_alpha1.0_rank4_noxattn_last:-4>, BREAK, smile, happy, dancing, brown skirt, brown coat, open mouth, BREAK, outseide, park, detailed background, <lora:SawyerCDDPXL:.5>, cute, looking away,
Prompt negativo
dangerdonkey, kkw-new-neg-v1.6 ,(low water quality:1.45), low particles effects, ( 3d render, anime, draw, cartoon, grotesque),( over saturated:1.9), jpeg artifacts, out of frame, score_6,score_5,score_4, (watermark:1.5), (text:1.5), , worst quality, low quality, bad anatomy, bad hands, missing fingers, fewer digits, source_furry, source_pony, source_cartoon,3d, blurry, film grin,monochromatic, sketch, drawing, 4 fingers, out of focus, 6 fingers,fat, hair buns, midget, chibi, nude, naked, nipples, human skin, against wall,
Ajustes
Sampler
DPM++ 2M SDE Karras
Pasos
30
Guidance
7
Semilla
1987784278098097000
Tamaño
1344x1728
Clip skip
2
Prompt
score_9, score_8_up, score_7_up, inside a cave, underground ruin, multicolored glowing mushrooms, detailed background, rocks, rain, wet, dripping, wet clothes, dark, overalldetailxl, moss, solo, BREAK, looking at viewer, 1girl, hornet \(hollow knight\), arthropod, exoskeleton, medium chest, skinny, black body, white mask, empty eyes, clothes, dirty, red cloak, sitting, holding_weapon, digitigrade, feet, 2 toes, reflections, stream, interior, warm tones
Prompt negativo
score_6, score_5, score_4, text, watermark, simple background, outdoors, sky, monochrome, greyscale
Ajustes
Sampler
DPM++ 2M Karras
Pasos
35
Guidance
7
Semilla
1318725318
Tamaño
768x1024
Prompt
score_9, score_8_up, score_7_up BREAK <lora:DBH_Chloe:0.75>, chloe, 1girl, blonde hair, beautiful girl, sleeveless, blue eyes
Prompt negativo
score_6, score_5, score_4, closest, head out of frame, ugly face, low res, blurry face, black and white, muscular female, watermark, bad hands, missing fingers, multiple views, extra hands, extra legs, extra fingers, eyewear on head
Ajustes
Sampler
DPM++ 2M
Pasos
39
Guidance
10
Semilla
919387310
Tamaño
832x1216
Prompt
score_9, score_8_up, score_7_up, (anubis god:1.55), anubis face, god rays, light, gold and black skin, sky, advntr, reelmech, mechanical parts, cable, wires, machinery, joints, body suit, glowing, glowing eyes, black hair, .score_9, score_8_up, score_7_up,score_6_up, <lora:RM_MechArmor_v1.8:0.7> Power Suit, Advanced Gear , Futuristic
Prompt negativo
core_6, score_5, score_4, BeyondSDXLv3
Ajustes
Sampler
DPM++ 3M SDE
Pasos
39
Guidance
10
Semilla
136345870
Tamaño
832x1216
Prompt
analog photo of Chinese girl, dutch angle, ( tattoo on whole body:1.3) , tradional clothes, <lora:MJ52:0.5>, .score_9, score_8_up, score_7_up,score_6_up,
Prompt negativo
core_6, score_5, score_4, BeyondSDXLv3
Modelos de IA para generar imagen, vídeo y texto
goddess realismpony1 xl es un modelo base para la familia Stable Diffusion XL 1.0 listado en ModelTrends.ai, un catálogo de solo lectura de modelos de IA de imagen, vídeo y texto de código abierto. Compáralo con otros modelos Stable Diffusion XL 1.0, consulta su puntuación de calor para ver su tendencia y ábrelo en PirateDiffusion o BitVector para probarlo.
Explorar por familia de modelos
Ver todos los modelos