Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
Exécuter en local
hassakuXLIllustrious_v21fix.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
AD
<hassaku21fix-xl>
À propos de ce modèle
STABLE DIFFUSION XL 1.0 · Modèles de base
Créé par
Ikena
sur Civitai
by Ikena - Hassaku XL (Illustrious)
Notes du créateur
Hassaku aims to be a anime model with a bright and distinct anime style. My for everything related to anime models and art. If you'd like to support my work, you can do so at: , every bit helps and is truly appreciated! ____________________________________________________________ Supporters: Thanks to my supporters tamashiicolle, pttcot, SETI and Kodokuna ____________________________________________________________ Using the model: - The model was trained primarily on images with minimal disruptive elements, such as floating text, logos, speech bubbles, or signatures. If any of these elements appear in an image, please include "signature" in your negative prompt. - Danbooru and franchise tags are not used in training, so please avoid using them in prompts. Metadata such as "highres" and franchise tags like "re:zero kara hajimeru isekai seikatsu" are not used in training. - A CFG scale between 3 and 7 is recommended. For best results, use CFG 6 with the Euler a sampler. - Refer to the example images, to understand, how the model should be used. - The model is designed to be simple and straightforward to prompt. Use the following tag order: - Number of characters - Character Tags - All remaining tags Example: 1girl, rem \(re:zero\), standing, masterpiece, upper body - Here are some resolution options for SDXL: - 1536 x 640 - 1344 x 768 - 1216 x 832 - 1152 x 896 - 1024 x 1024 - 896 x 1152 - 832 x 1216 (most recommended) - 768 x 1344 - 640 x 1536 Lora use: - NoobAIs Loras working for the most part better in compare to - Versions 2 and 3 is less compatible to most loras trained on Illustrious or Noob, because it got further trained away of both. Style A is still the most compatible for it. ______________________________________________________ Version and License info: - Below V1 merges - Version V1 use & with additional training - V2 is trained on its own and don't include any extra merge. Base was V1, it is trained to include newer or missing characters. It was also used for further training tests - V3 is a merge of and V2.2, to fix some issues and was also trained to include newer or missing characters All Models using the license.
27,326 téléchargements · 3,340 j'aime sur Civitai
SHA256
847403D47A488C22AE095A64648AD62A78F47B35A71B9E752071E5E2ACDE56C3
ID de modèle ModelTrends.ai
#19443
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 Karras
Étapes
29
Guidance
3.5
Seed
1663052538
Taille
832x1216
Clip skip
2
Prompt
masterpiece, ultra-HD, cinematic lighting, photorealistic, impressionism (1.5), high detail, depth of field, (blurred background), (dramatic lighting),masterpiece, best quality, very aesthetic,8k,lae'zel, 1girl, gith (d&d), slit pupils, yellow eyes, facial mark , pointy ears, scar on face, scar on mouth, scar on forehead, braided sidelock, brown hair, colored skin, body freckles, toned, dungeons & dragons, medium breasts, reflection, wet, relaxed, dappled sunlight, outdoors, shoulder armor, armor, ridding a red dragon, flying over lake, masterpiece, best quality, amazing quality, usnr,
Prompt négatif
worst quality, low quality, displeasing, text, , watermark, bad anatomy, text, artist name, signature, hearts, deformed hands, missing finger, shiny skin,child,children,
Réglages
Sampler
DPM++ 2M
Étapes
30
Guidance
5
Taille
1280x1856
Poids utilisé
1
Prompt
Masterpiece, absurdres, highest quality, highly detailed, newest, 8k, cartoon style, vivid colors, closeup, animal, Scrat, long snout, bushy tail, bulging eyes, manic expression, open mouth, intense expression, black eye mask, burglar outfit, tongue out, striped tail, holding a big brown acorn, running, police cars in the background, flashing police lights, police chase, flashing red and blue lights in the background, urban setting, motion lines, detailed background, dynamic angle, night,
Prompt négatif
anthro, humanoid, mangled body, low quality, low res, blurry, sketch, watermark, signature, red shirt, t-shirt, bright, simple background, plain background, human, nipples, blue head, female, girl, anthro
Réglages
Sampler
DPM++ 2M
Étapes
30
Guidance
5
Seed
1307556808
Taille
832x1216
Prompt
amazing quality, very aesthetic, illustration, perfect composition, intricate details, absurdres, incredibly absurdres, 1girl, solo, (office, red room, indoor, throne), Lucifer (Helltaker), (smirk, teeth, white hair, long hair, blunt bangs, black tiara, red eyes, looking at viewer), (suit and tie, red shirt, black jacket, black pants), (sitting, crossed legs, need_buzz, holding sign, <lora:NeedBuzz_sign_Illustrious:1>), <lora:VanripperIllustriousXL_byKonan:1>
Prompt négatif
leotard, multiple girls, 2girls, multiple views, worst detail, sketch, censor, text, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, (extra digit, fewer digits:1.2), cropped, lowres, (worst quality, bad quality:1.2), bad anatomy, jpeg artifacts, signature, watermark, username, conjoined, extra toes, extra fingers, extra toes, childish, ponytail, taneline, colored body, tattoo
Réglages
Sampler
DPM++ 2M Karras
Étapes
29
Guidance
3.5
Seed
1663052541
Taille
832x1216
Clip skip
2
Prompt
masterpiece, ultra-HD, cinematic lighting, photorealistic, impressionism (1.5), high detail, depth of field, (blurred background), (dramatic lighting),masterpiece, best quality, very aesthetic,8k,lae'zel, 1girl, gith (d&d), slit pupils, yellow eyes, facial mark , pointy ears, scar on face, scar on mouth, scar on forehead, braided sidelock, brown hair, colored skin, body freckles, toned, dungeons & dragons, medium breasts, reflection, wet, relaxed, dappled sunlight, outdoors, shoulder armor, armor, ridding a red dragon, flying over lake, masterpiece, best quality, amazing quality, usnr,
Prompt négatif
worst quality, low quality, displeasing, text, , watermark, bad anatomy, text, artist name, signature, hearts, deformed hands, missing finger, shiny skin,child,children,
Réglages
Sampler
Euler a
Étapes
35
Guidance
6
Seed
1164913661
Taille
832x1216
Clip skip
2
Prompt
masterpiece, best quality, amazing quality,general, nun, beach, sunlight, limited palette,
Prompt négatif
extra digits, wide hips, thick thighs, crossed legs, pool ladder, worst quality, low quality, bad quality, very displeasing, lowres, artistic error, bad, fewer, extra, missing, signature, username, watermark, blurry, jpeg artifacts, aliasing, cropped, guro, ugly, deformed, sketch, unfinished, censored, outline
Réglages
Sampler
Euler a
Étapes
20
Guidance
7
Seed
3217542355
Taille
896x1152
Prompt
1girl, fox tail, sky, white hair, long hair, animal ears, masterpiece, yellow eyes, kitsune, parted lips, looking at viewer, kimono, floral print, outdoors, arms behind head, adjusting hair, cloud, volumetric lighting, blue sky, portrait, upper body,
Prompt négatif
worst quality, bad quality,
Modèles d'IA pour générer image, vidéo et texte
hassaku21fix xl est un modèle de base pour la famille Stable Diffusion XL 1.0, 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 XL 1.0, 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