Model
Trends
.ai
Model
Trends
.ai
cele mai bune modele AI open source
Rulează local
aamAnyloraAnimeMixAnime_v1LCM.safetensors
1.99 GB · SafeTensor · fp16 · pruned
Descărcările sunt servite de Civitai. Unii creatori cer mai întâi autentificarea pe Civitai.
Despre acest model
STABLE DIFFUSION 1.5 · Modele de bază
Creat de
Lykon
pe Civitai
AAM - AnyLoRA Anime Mix - Anime Screencap Style LCM Model by Lykon.
Notele creatorului
AnyLoRA Anime Mix (AAM) Anime Screencap Style Model Do you like what I do? Consider supporting me on 🅿️ or feel free to ☕. A ❤️, a kind comment or a review is greatly appreciated. Please check out too Purpose of this model - Make amazing anime style artworks on its own. - Train character loras where the dataset is mostly made of anime screencaps, allowing less anime style transfer and less overfitting. - Use anime styles if the lora is "weak" and doesn't give enough flat coloring. - It's also pretty good at generating hentai stuff. Suggested settings - Set the ETA Noise Seed Delta (ENSD) to 31337 - Set CLIP Skip to 2 - DISABLE face restore. It's terrible, never use it - Use negative prompts and embeddings that don't ruin the style - Use AnimeVideo or Foolhardy as upscalers. If you know what to do, Latent makes an interesting effect (see the first example and the Miku one) - (optional to reproduce some results) Set "Do not make DPM++ SDE deterministic across different batch sizes." Only my old images use that. (this setting is not actually good, so I'm gonna disable it, but might be the reason some results are different) LCM version Use it with 5-15 steps, ~2 cfg. LCM VERSION WORKS ONLY WITH LCM SAMPLER (to get it on Auto1111 you currently need a plugin). Being a distilled model it has lower quality compared to the base one. However it's MUCH faster and perfect for video and real time applications. Brief history Chatting on Discord, I noticed my Mushoku Tensei style LoRA, while trained on AnyLoRA, was performing a bit better on CyberAlchemist's AnimeMix base model. I read on his HF that the model was a supermerge of AnythingElse, his AnimeMix lora and various other style loras. Since AnimeMix was already including many of my old anime style loras, I wanted to experiment and try to make a model that could maximize the result of my Mushoku Tensei style, going beyond what AnyLoRA and AnimeMix could do. After testing many different versions, adjusting the settings and receiving feedback from the Discord channel, I ended up with a version that works very well on anime loras trained on AnyLoRA (base). Especially my Mushoku Tensei one which felt very weak on AnyLoRA. I don't advise using this for anime style training (limit to generation after training it on AnyLoRA or NAI), but it might actually be fairly good for character loras where your dataset is made mostly of anime screencaps. It should technically reduce the anime style impact making the character lora less overfitted. I'll definitely experiment with it in the following weeks.
3,233 descărcări · 915 aprecieri pe Civitai
SHA256
997EA7C1D2341431F3FBE7DD31F3EDB9DD3A5EBE90F13EBEAA39734A11CE60E9
ID model ModelTrends.ai
#9101
Semnalează conținutul
Exemple de randări
Prompturi și setări partajate de cei care au făcut aceste randări pe Civitai. Alege o randare pentru a vedea cum a fost făcută.
Setări
Sampler
LCM Test
Pași
15
Guidance
2
Seed
4002152246
Mărime
512x704
Clip skip
2
Prompt
mio \(xenoblade\), 1girl, animal ears, bare shoulders, grey hair, braid, breasts, fingerless gloves, gloves, jacket, looking at viewer, off shoulder, open mouth, short hair, solo, white gloves, yellow eyes, <lora:mio:0.6>
Prompt negativ
(low quality, worst quality), FastNegativeV2
Setări
Sampler
LCM Test
Pași
15
Guidance
2
Seed
4002152246
Mărime
512x704
Clip skip
2
Prompt
megumin, 1girl, bare shoulders, black cape, black gloves, black hair, blush, cape, choker, collarbone, dress, fingerless gloves, gloves, hair between eyes, hat, long sleeves, looking at viewer, medium hair, off-shoulder dress, off shoulder, red dress, red eyes, sidelocks, simple background, solo,white background, witch hat, ((masterpiece))
Prompt negativ
(low quality, worst quality), FastNegativeV2
Setări
Sampler
LCM Test
Pași
15
Guidance
2
Seed
4002152246
Mărime
512x704
Clip skip
2
Prompt
cyberpunk edgerunners, 1girl, lucy \(cyberpunk\), bare shoulders, blue eyes, breasts, leotard, looking at viewer, medium breasts, off-shoulder jacket, off shoulder, red eyeliner, short hair, sleeveless turtleneck leotard, solo, turtleneck leotard, white hair, ((masterpiece)) <lora:cyberpunk_edgerunners_offset:1> <lora:lucy_offset:0.6>
Prompt negativ
(low quality, worst quality), FastNegativeV2
Setări
Sampler
LCM Test
Pași
15
Guidance
2
Seed
565444249
Mărime
536x744
Clip skip
2
Prompt
masterpiece, best quality, hatsune miku, upper body,
Prompt negativ
EasyNegative, tattoo, (shoulder tattoo:1.0), (number tattoo:1.3), frills
Setări
Sampler
LCM Test
Pași
15
Guidance
2
Seed
2815559746
Mărime
512x640
Clip skip
2
Prompt
mushoku tensei style, 1boy, male focus, solo, green eyes, window, ahoge, blonde hair, indoors, looking at viewer, hood, upper body, brown hair, hood down, ((masterpiece)) <lora:mushoku_tensei_style_offset:1>
Prompt negativ
(low quality, worst quality), FastNegativeV2
Setări
Sampler
LCM Test
Pași
15
Guidance
2
Seed
4002152247
Mărime
512x704
Clip skip
2
Prompt
kitagawa marin, 1girl, :d, upper body, bead bracelet, beads, black necktie, blonde hair, blue skirt, blush, bracelet, hand on own hip, jewelry, long hair, looking at viewer, necktie, open mouth, plaid, plaid skirt, red eyes, school uniform, shirt, outdoors, skirt, smile, solo, standing,white background, white shirt, ((masterpiece))
Prompt negativ
(low quality, worst quality), FastNegativeV2
Modele AI pentru generare de imagini, video și text
lcm aam este un model de bază pentru familia Stable Diffusion 1.5, listat pe ModelTrends.ai, un catalog doar pentru citire al modelelor AI open source pentru imagini, video și text. Compară-l cu alte modele Stable Diffusion 1.5, verifică-i scorul de căldură pentru a vedea cât este de popular și deschide-l pe PirateDiffusion sau BitVector pentru a-l încerca.
Răsfoiește după familia de modele
Răsfoiește toate modelele