New
Everything new in AI as it appears: launches announced by the labs, brand-new models, datasets, papers and open-source tools. Checked every minute or two. Launches feed · Trending · News
Live now
- Connecting…
Yesterday
- Model
- Modeltefpestana/KR2 - Aniimo Eklue
Nice pet collection f2p, cute, cozy, easy but with secondary challenging modes, events, puzzles, stories and secrets to unlock. This LoRA is for fans. Please, do not use
- Model
- ModelAIKSK/MOSS-Image 50/8/4-Step Comparison Lab
Compare three connected MOSS-Image SFT generation paths in one ComfyUI graph. The branches share prompt, seed 4242, and a 1024 x 1024 latent canvas, then save separate 50
- ModelAI_of_Skadi/Shion Suminoe
About Shion Not Shioff She has 2 hairstyles
- ModelAIKSK/Kromoss 8-Step Text-to-Image
A compact Kromoss text-to-image recipe pairing the Kromoss INT8 model with the connected DMD2 acceleration LoRA. Its active sampler is set to eight diffusion steps. Main
- ModelAIKSK/MOSS-Image Beauty Portrait Workflow
Create beauty-oriented portraits with a MOSS-Image SFT text-to-image graph. The connected Beauty LoRA lets you explore makeup, skin appearance, and portrait styling from
- ModelAIKSK/MOSS-Image SFT Style Lab
Experiment with style changes by applying a rank-256 SFT difference LoRA to the MOSS-Image SFT base workflow. This is an editable text-to-image recipe for comparing visua
- Model
- ModelAIKSK/MOSS MAX ULTRA QHD Text-to-Image
A high-resolution MOSS-Image text-to-image workflow using the MAX ULTRA LoRA. The active graph starts from a 2560 x 1440 latent canvas and saves a generated image. Main f
- Modelshow3140/Danbooru-style Very AWA waifu workflow【DanVAw】
This workflow uses "hires.fix" by default to achieve optimal results for anime-style images (including those with oil painting or watercolor aesthetics). More precisely,
- Model
- ModelAIKSK/MOSS-Image CharRef v2 Character Reference
Generate a new character image from an uploaded reference picture and an editable prompt. This ComfyUI graph uses MOSS-Image Base with the connected CharRef v2 LoRA and a
- Model
- ModelNeuralNonsense/Olga Dmitrievna | Everlasting Summer
Krea 2 Recommended weight: 0.75-1.00 Code tag: OlgaES Appearance: long dark red hair, green eyes, tanned skin, large breasts Main outfit: white short-sleeved collared shi
- Model
- Modelmuell659/marie-ann wet hair wet portrait
Makes ladies beautyful hairstyles soaking wet
- Model
- Model
- Model
- Model
- Model
- Model
- Model
- Model
- Model
- Modelxion1/ntrchef style [IL, Z-Image, Anima, Krea 2, MOSS]
Supposed to emulate style of ntr_chef, if you know, you know Illustrious: v1.0 and v2.0 works best in conjunction with ShinyHero's LoRA at weights 0.5-0.9 v3.0 is pretty
- Model
- Model
- Model
- Model
- Model
- Model
- Modelukr8b3g201/MOSS_LUC
Moss Image Luc [sft int8 convrot V.1 ] An anime -focused MOSS-Image merge from my Lucy series , quantized to INT8 with convrot after merging. Best suited for anime and il
- Modelnnhhh8y5/Mokemoke Style | Anima
Mokemoke style lora. Use ComfyUI pipeline.
- Modeltabinezumi/power_loader (alien) ANIMA LORA
001 小ネタで作成した物なので動かしたりは出来ません
- Model
- ModelEmilyMars/Fluffy Heartbeat | Shining Nikki
Works best at 0.75 weight. If you want a model or wish to support me, commissions are open: https://civitai.com/articles/22388/commissions-are-open
- Model
- Model
Headlines and links come from the labs' own blogs, Hacker News and the GDELT news index, and from the sources our index already follows. We show a short excerpt and always link to the original. A launch reported by a news site rather than the lab is marked “Reported” until the lab itself announces it.