Engines and Tools

Unsloth v0.1.901-beta Released: Major LoRA Memory Reductions

Unsloth v0.1.901-beta is released, featuring massive LoRA memory reductions for 4-bit checkpoints, a desktop command ...

Image, Video and Audio

QI_2.1_AnyAngle Camera Angle Control LoRA: 48GB+ VRAM, File List

Learn about QI_2.1_AnyAngle, a LoRA for Qwen-Image-2.1 that allows changing camera angles in generated images while p ...

Image, Video and Audio

LongLive-Plug-Wan2.1-T2V-14B-few-step: Our Generated Video, File List

Learn about LongLive-Plug-Wan2.1-T2V-14B-few-step, a new LoRA adapter for Wan2.1-T2V-14B designed for faster, few-ste ...

Image, Video and Audio

LongLive-Plug-Wan2.1-T2V-14B-cfg: Our Generated Video, File List

Learn about LongLive-Plug-Wan2.1-T2V-14B-cfg, a LoRA adapter for Wan2.1-T2V-14B designed to distill Classifier-Free G ...

Image, Video and Audio

LongLive-Plug-Wan2.2-TI2V-5B-cfg: Our Generated Video, File List

A CFG-distilled LoRA adapter for Wan2.2-TI2V-5B that reduces DiT forward passes to one per step, improving inference ...

Image, Video and Audio

LongLive-Plug-Wan2.2-TI2V-5B-few-step: Our Generated Video, File List

Efficient-Large-Model has released LongLive-Plug-Wan2.2-TI2V-5B-few-step, a Generator LoRA enabling 4-step video gene ...

Image, Video and Audio

MiniMax-H3-Character-Swap-LoRA Character Swap LoRA Adapter: File List

Discover akatz-ai/MiniMax-H3-Character-Swap-LoRA, an experimental LoRA adapter for the MiniMax H3 video generation mo ...

Image, Video and Audio

Qwen-Image-2.1-viggle-turbo Image Generation Model: 48GB+ VRAM

Viggle has released the v0.1 preview of Qwen-Image-2.1-viggle-turbo, a 4-step distilled image generation and editing ...

Engines and Tools

LocalAI v4.10.0 Released: Fleet Dashboard & M5 Support

LocalAI v4.10.0 is out, featuring a fleet management dashboard, Apple M5 startup crash fixes, credential file managem ...

Image, Video and Audio

yue2-mothersuperior-realaudio-tokenizer-v4: 12GB+ VRAM, File List

Mothersuperior has released a real audio toolkit for the open music generation model YuE2-3B, enabling tokenization a ...