Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
Exécuter en local
ponyDiffusionV6XL_v615.safetensors
1.99 GB · SafeTensor · fp16 · pruned
kl-f8-anime.ckpt
386 MB · Other
Télécharger
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
AD
<ponydiffusion-sd15>
À propos de ce modèle
STABLE DIFFUSION 1.5 · Modèles de base
Créé par
PurpleSmartAI
sur Civitai
Pony Diffusion V6-1.5 model by PurpleSmartAI. Make sure you load this model with clip skip 2 (or -2 in some software), otherwise you will be getting low quality blobs. This model is capable of recognizing many popular and obscure characters and series. If you are looking specifically for pony style, I recommend using one of the two following templates anthro/feral pony, rest of the prompt or source_pony, rest of the prompt. This model is trained on combination of natural language prompts and tags and is capable of understanding both, so describing intended result using normal language works in most cases, although you can add some tags after the main prompt to boost them.
Notes du créateur
(and don't worry, coming to your computer very soon - Astra) Pony Diffusion V6 is a versatile SDXL finetune capable of producing stunning SFW and NSFW visuals of various anthro, feral, or humanoids species and their interactions based on simple natural language prompts. CHECK "ABOUT THIS VERSION" ON THE RIGHT IF YOU ARE NOT ON "V6" FOR IMPORTANT INFORMATION. and or . Important information Make sure you load this model with clip skip 2 (or -2 in some software), otherwise you will be getting low quality blobs. This model supports a wide array of styles and aesthetics but provides an opinionated default prompt template that allows generation of high quality samples with no negative prompt and otherwise default settings score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, just describe what you want, tag1, tag2 (previous Pony Diffusion models used a simpler score_9 quality modifier, the longer version of V6 XL version is a training issue that was too late to correct during training, you can still use score_9 but it has a much weaker effect compared to full string. You can learn more about these tags ). The model is designed to not need negative prompts in most cases and does not need other quality modifiers like "hd", "masterpiece", etc... Other special data selection tags include, 'source_pony', 'source_furry', 'source_cartoon' and 'source_anime' and ratings of 'rating_safe', 'rating_questionable' and 'rating_explicit'. This model is capable of recognizing many popular and obscure characters and series. If you are looking specifically for pony style, I recommend using one of the two following templates `anthro/feral pony, rest of the prompt` or `source_pony, rest of the prompt`. This model is trained on combination of natural language prompts and tags and is capable of understanding both, so describing intended result using normal language works in most cases, although you can add some tags after the main prompt to boost them. Using Euler a with 25 steps and resolution of 1024px is recommended although model generally can do most supported SDXL resolution. This model will sometimes generate pseudo signatures that are hard to remove even with negative prompts, this is unfortunately a training issue that would be corrected in future models. If that's an issue for you I suggest trying V5.5 or inpainting. Special thanks - Iceman for helping to procure necessary training resources - Haru for assistance with captioning efforts - Cookie for technical expertise in training - PSAI Server Subscribers for supporting the project costs - PSAI Server Moderators for being vigilant and managing the community Technical details The model has been trained on ~2.6M images aesthetically ranked based on authors personal preferences, with roughly 1:1 ratio between anime/cartoon/furry/pony datasets and 1:1 ratio between safe/questionable/explicit ratings. About 50% of all images has been captioned with high quality detailed captions, which results in very strong natural language capabilities. All images has been trained with both captions (when available) and tags, artists' names have been removed and source data has been filtered based on our Opt-in/Opt-out . Any explicit content involving underage characters has been filtered out. License This model is licensed under a modified Fair AI Public License 1.0-SD() license. The following modifications have been added to Fair AI Public License: You are not permitted to run inference of this model on websites or applications allowing any form of monetization (paid inference, faster tiers, etc.). This applies to any derivative models or model merges. If you want to use this model commercially, please reach us at . Explicit permission for commercial inference has been granted to and .
34,788 téléchargements · 548 j'aime sur Civitai
SHA256
2130162F1B5660401FDA01FF07C22249F2673BC22C3E43C36CFC5583B5A802AE
ID de modèle ModelTrends.ai
#8693
Signaler le contenu
Rendus d'exemple
Prompts et réglages partagés par les personnes qui ont réalisé ces rendus sur Civitai. Choisissez un rendu pour voir comment il a été fait.
Réglages
Sampler
Euler a
Étapes
30
Guidance
7
Seed
2928318006
Taille
768x768
Prompt
score_9, show accurate, cute pony portrait, simple white background
Réglages
Sampler
Euler a
Étapes
40
Guidance
7.8
Seed
462446907
Taille
400x600
Clip skip
2
Prompt
score_9, score_8_up, score_7_up, (AS-YoungV2:0.2), 8k, rating_safe, photorealistic, high resolution, masterpiece, highest quality, high detail, (pinup posing:1.3), (android:1.2), (excellent anatomy:1.3), ( jenny wakeman:1.5), (robot joints:1.1), (a sexy:1.2), 18 years old , twintails, thin body, skinny, petite, oversized purple sweater, boots, cute, on floor, aesthetic, (standing:1.4), confused, lonely, tired, dazed, well lit, bright lighting, in an office, cute, drunk, wide angle, <lora:robot_skin_v1.0:0.55> <lora:jenny wakemanv1.1:0.9>
Prompt négatif
score_6, score_5, score_4, easynegative, negative_hand-neg, ng_deepnegative_v1_75t,( nose:1.2),mutated, limbs mutation, fused, fused limbs, ugly face, bad quality, normal quality, low res, blurry face, black and white, watermark, nude, long neck, wide neck, bad anatomy, headphones, bad detailed background, poorly drawn, big breasts, asymetric twintails,
Réglages
Sampler
Euler Karras
Étapes
40
Guidance
7
Seed
1749521948
Taille
1024x1280
Prompt
1girl, Raviel, red eyes, white hair, long hair, long eyelashes, black dress, the character is depicted in profile, (morning garden full of flowers background: 1), (formed average breasts: 1), petite body, (happy smile), (humility: 1.2), tight clothes, bulging breasts, (skinny: 1.1), shy, score_8, score_7_up, score_6_up, (masterpiece, best quality, very aesthetically pleasing, ultra-detailed), beautiful face, detailed eyes, morning garden full of flowers background, expressive, shiny skin
Prompt négatif
score_6, score_5, score_4, busty, ugly face, mutated hands, low res, blurry face, pumped body, black and white, (((extra fingers))), 6 fingers, cleavage, long neck, stretched neck, nipple, window, indoors
Réglages
Taille
832x1120
Prompt
Stationary CCTV recording with a blinking recording light focusing on Revy from Black Lagoon, who grins sadistically at the camera. Her pistol is smoking. The camera pans to the side to show two defeated goons on their backs.
Prompt négatif
made with Dreamina
Réglages
Sampler
DPM++ 2M SDE Karras
Étapes
40
Guidance
7
Seed
3274371848
Taille
832x1216
Clip skip
2
Prompt
score_9, score_8_up, score_7_up, score_6_up, realistic, 1 pegasus, horn on head, forest, night, fantasy, magic, dutch view, <lora:Photo 2 Style SDXL_LoRA_Pony Diffusion V6 XL:1> <lora:Photo_2_Style_SDXL_LoRA_Pony_Diffusion_V6_XL:1>
Prompt négatif
score_5_up, score_4_up, poorly drawn, bad anatomy, bad proportions, watercolor painting, brush strokes, 3d, colorless, glitch, blurry, signature, watermark, bad face, distorted face, messed up eyes, deformed
Réglages
Sampler
Euler a
Étapes
30
Guidance
5
Seed
1292222438
Taille
1016x512
Prompt
princess celestia, feral alicorn, standing, elegant, white fur, concave belly, sash, pink dress, gold earrings, diamonds, score_9, lace, silk, gauze, open wings, interior, throne room, <lora:oil painting bichu-v0612:.5>
Prompt négatif
mutant, blurry, ugly, deformed, text, signature, chibi, five legs, six legs, noise
Réglages
Sampler
Euler a
Étapes
1521
Guidance
30
Seed
77
Taille
342x866
Prompt
Jimmy Crystal an main antagonist of Illumination's eleventh animated feature 3D adult powerful muscular Arctic white wolf with striking blue eyes, distinctive attire includes a shiny black suit complemented by a white collared shirt and a white handkerchief in the pocket, and often sports two neckties: one in pure black and the other in red magenta, patterned with gold guitar picks featuring his initial (C), completing his ensemble are shiny black pants and polished black leather suit shoes, described as hard-nosed and overzealous, an adult Arctic white wolf with striking blue eyes Jimmy Crystal is willing to go to any lengths to produce grand shows and is a tough crowd-pleaser, demeanor becomes menacing and threatening when urging someone to act swiftly, no human figures., close-up portrait, close-up shot, low-angle shot., muscular powerful physique evil body white arctic wolf Jimmy Crystal with icy blue eyes wear black neckties and have no tiger striped
Prompt négatif
ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, blurry, bad anatomy, blurred, watermark, grainy, signature, cut off, draftstriped wolf, no adult tiger cub, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, blurry, bad anatomy, blurred, watermark, grainy, signature, cut off, draft, ugly, deformed, noisy, blurry, distorted, out of focus, bad anatomy, extra limbs, poorly drawn face, four eyes, poorly drawn hands, missing fingers, cartoon, disfigured, bad art, deformed, poorly drawn, extra limbs, close up, b&w, weird colors, blurry, watermark, rotten ugly wolf, blurry, bad anatomy, extra limbs, poorly drawn face, poorly drawn hands, missing fingers, humans,no multi faces and two faces wolf, any colors suits/pants and wear ties or ribbon,ugly, tiling, poorly
Réglages
Sampler
Euler a
Étapes
35
Guidance
8
Seed
156680208700286
Taille
768x1024
Prompt
score_9, jinx \(league of legends\), looking at viewer, realistic eyes, high quality, best quality
Prompt négatif
text, watermark, logo, worst quality, bad quality, normal quality, blurry, pixelated, lowres, jpeg artifacts, scan artifacts, simple background
Modèles d'IA pour générer image, vidéo et texte
ponydiffusion sd15 est un modèle de base pour la famille Stable Diffusion 1.5, référencé sur ModelTrends.ai, un catalogue en lecture seule de modèles d'IA open source pour l'image, la vidéo et le texte. Comparez-le aux autres modèles Stable Diffusion 1.5, consultez son score de chaleur pour suivre sa tendance et ouvrez-le sur PirateDiffusion ou BitVector pour l'essayer.
Parcourir par famille de modèles
Voir tous les modèles