Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
Exécuter en local
arthemyComics_v70Baked.safetensors
1.99 GB · SafeTensor · fp16 · pruned
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
AD
<comics-vision>
À propos de ce modèle
STABLE DIFFUSION 1.5 · Modèles de base
Créé par
Arthemy
sur Civitai
Comics Vision v3 by Aledelpho Comics Vision (previously known as Toontanium) is a full checkpoint base model, a blend of models like MissToon and Icomix. As such, it serves as a good western-style illustration base model that's right on the edge of anime. The optional trigger Toontanium can alter the results, but is not included by default. For best results, render directly at 640x768 and then /facelift /anime with the ones you like. Here's prompting advice directly from the model's creator, Aledelpho: Start from the prompt of the pictures I've uploaded and then customize the areas focused on Character, Setting, Emotions, Colors and Aesthetic. For example: (inked original-art:1.2), (lineart:1.33),1woman,space-viking society, blonde braid strong manly woman barbarian,wrinkles,(depth),(movement:1.4),cinematic-composition,snob smirk,(hyperdefined),intricate-setting,undercut,yellow white orange,winter futuristic-city-streets,(thin-lines),viking-sci-fi aesthetic,neon-lighting,stars,giant-robots-machines,(fine-details:1.3),RAW-format,emotional,(muted-colors) Update v3: # To get crispier results use: /more /size:1200x1200 /images:4 /strength:0.45 on your favourite pictures. # Version 3 offers better quality and colour saturation while perfectly capturing the spirit of its predecessor.
Notes du créateur
Generate pictures with Arthemy Searching for an AI characters generator? Arthemy, my AI image generator now has all of my models loaded and ready to be tried on your browser - no GPU required ----> ✦ Comics Arthemy - Quick Start ✦ 1_____ I highly suggest to use this embeddings: - verybadimagenegative_v1.3 2_____Size: Around 640 x 768 3_____Prompt: Start from the prompt present here and tune the results based on your needs: - Quick Prompt: [How],[what/who],[where],[other] exaple: (ultradetailed fantasy illustration:1.3), elf witch woman with a large hat and purple dress, on a snow-covered mountain with blowing wind, complex lighting and strong sense of movement - Quick Negative Prompt: verybadimagenegative_v1.3, (worst quality:1.4),(low quality:1.4),(normal quality:1.3),lowres,watermark, title, (jpeg-artifacts:1.3) 4_____Upscale: to get crisp results like the one shown in the pictures use HiResFix and Lanczos. I suggest to use this step only on the preferred pictures, since it's quite heavy on the performance side. I hope you like my merge and I can't wait to see what you all are going to create with it! For future update, about the AI Editor I'm building with an italian team and my models you can check: ____________________________________ Merged / subtracted / inspired by Models: DarkArtsStyle - DiffusionBrushEverything - ForgottenMixtheNovelist - Icantbelieveits - icomix - mcbsMachinecodesComics - OccidentalMix V2.0 - vividwatercolors - westerncartoontypeA - Babes - Diffusion Brush Everything - Cute Cartoon - Western animation diffusion - IdentityCrisis - Vivid Watercolors - Exquisite details极致华彩 - SXZ Luma - + some of my old mix Some of these models have been used for subtraction, but they all have been useful in order to create this model. If you like Comics Vision, remember to check these other models and consider to support their creators!
671 téléchargements · 30 j'aime sur Civitai
SHA256
A08A577280D669B1C6E08C75DB96AB0B0BFF4A0518DE9D921ACF3ED49E5536DD
ID de modèle ModelTrends.ai
#628
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
DPM++ 2M SDE
Étapes
26
Guidance
7
Seed
908768910
Taille
512x768
Clip skip
3
Prompt
expressionism art stylized by Bill Sienkiewicz and Henri Le Fauconnier, delightful woman, pink hair, Victorian, dark humor, horror comics
Prompt négatif
lowres, text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, out of frame, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, username, watermark, signature
Réglages
Sampler
DPM++ 2M SDE Heun Exponential
Étapes
50
Guidance
5.5
Seed
879518548
Taille
600x864
Prompt
(exciting graphic novel style:1.3), portrait, an elf princess with a (snob grin, teeth.1.2), messy green hair, tiara, antlers,crown and medallions, noble velvet black dress, surrounded by mist,orange and red backlight, steam, (playful charismatic), strong complex light, contrast shadows, in front of a chaotic porta
Prompt négatif
desaturation, grayscale, noise, monochromatic, fruit, (simple background.1.2), heterochromia, verybadimagenegative_v1.3, (worst quality:1.4),(low quality:1.4),(normal quality:1.3),lowres,watermark, title, (jpeg-artifacts:1.3)
Réglages
Sampler
DPM++ 2M SDE
Étapes
26
Guidance
5
Seed
2306138133
Taille
896x1152
Prompt
expressionism art stylized by Bill Sienkiewicz and Henri Le Fauconnier, Delightful Female inside a Display case, Pink hair, Victorian, Action, Dark humor, Horror comics
Prompt négatif
lowres, text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, out of frame, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, username, watermark, signature
Modèles d'IA pour générer image, vidéo et texte
comics vision 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