
New LoRAs
Fresh LoRAs for image and video generation, every day.



Qwen3.8-Flash-Next-Brisk-Coder
an optimized version for programming and agent tasks



actionproof-proc-a12-state-reward-s1
LoRA adapter for database agent action verification



Krea2 / Kroma / Chroma - Fine Tactile Brushwork
tactile painting and textured brushstrokes
18+
Grimm's Fantasy: A versatile fantasy and sci-fi LoRA
Grimm's Fantasy is a LoRA (a small fine-tuning add-on for a base model) designed to generate detailed illustrations in fantasy and sci-fi styles. Built on Krea 2, the model specializes in intricate worlds, cinematic characters, and futuristic landscapes.
18+
Ocean Blue: Blue3
Qwen2.5 fine-tune focused on coding and self-distillation


18+

giocorte/totem-kiosk-extractor-sft-v2: LoRA adapters for ticket kiosks built on Qwen3
This release introduces two new LoRA adapters (lightweight fine-tunes built on top of a base model) trained jointly on an expanded dataset for an automated ticketing kiosk powered by Qwen/Qwen3-4B-Instruct-2507.


NeyroLearn
@neyrolearn
New models from Hugging Face every morning: video, images, LoRAs and LLMs with examples and links.
- Posts
- 1067
- Tags
- 59
Trending
Most liked on Hugging Face this week
- 1Add Micro Details
Images · 8.4K
18+ - 2MiniMax-H3
Video · 7.2K

- 3Flat Color - Style
Images · 6.2K

- 4Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF
Computer vision · 3.5K

- 580s Fantasy Movie
Images · 3.1K
18+
Popular tags
- #finetune1740
- #LLM1333
- #models1286
- #LoRA1067
- #Qwen923
- #images583
- #txt2img480
- #robotics467
- #VLM346
- #audio269
- #NSFW206
- #Krea192
- #video181
- #MiniMax_H3166
- #ComfyUI155
- #Gemma139
- #turbo127
- #MOSS_Image123
- #ASR107
- #TTS98
What a LoRA is and what we post here
A LoRA is a small add-on for a large model that teaches it a new style, character, motion or task without retraining the whole model. LoRAs are dozens of times smaller than the base model and plug into it, for example in ComfyUI.
This page collects new LoRAs from Hugging Face: for image generation on FLUX, Qwen Image, SDXL and Krea, for video on Wan and MiniMax H3, plus LoRA adapters for language models. Each post names the base model the LoRA fits, with examples and a download link.
Looking for a specific model? Paste its name or Hugging Face link into search, or describe your task to the assistant on the home page.
























