MiniMax-H3-Image-Character-Swap Image Editing Model: 4GB+ VRAM
A look at the MiniMax-H3-Image-Character-Swap checkpoint, which merges a character-swap LoRA into the MiniMax-H3-Imag ...
TTS-V5 Chinese TTS Model: 4GB+ VRAM, File List
An overview of autotrust/TTS-V5, a text-to-speech experimental model fine-tuned from Fun-CosyVoice3-0.5B-2512 for Chi ...
TTS-V4 Chinese Text-to-Speech Model: 8GB+ VRAM, File List
A Chinese text-to-speech model, autotrust/TTS-V4, has been released on Hugging Face, optimized for call center script ...
TTS-V3 Phone-Dialogue Specialized TTS Model: 8GB+ VRAM, File List
Learn about autotrust/TTS-V3, a Hugging Face model for voice cloning and conversational text-to-speech based on Qwen/ ...
MiniMax-H3-Image 16-Megapixel Image Generation Model: 4GB+ VRAM
An optimized and repackaged version of the image generation model MiniMax-H3-Image has been released for ComfyUI. Not ...
WeVisOne-VL Vision-Language Model: 8GB+ VRAM
Model files for Comfy-Org/WeVisOne-VL have been released for ComfyUI, bringing object-to-pixel visual perception capa ...
llama-modchip v2.4.0 Released for CPU Inference of Large MoE
Version v2.4.0 of llama-modchip brings CPU inference for massive MoE models like DeepSeek-V4-Flash on 64GB RAM.
Qwen3.8-27B-DSpine-b16 Draft Model for Speculative Decoding: 8GB+ VRAM
Explore tencent/Qwen3.8-27B-DSpine-b16, a draft model for speculative decoding using the DSpine method to accelerate ...
Pyramid-JiT: A 2B Text-to-Image Model Trained for $21K
Explore Pyramid-JiT, a 2B text-to-image model by Linum AI trained for $21K without a VAE. Read community reactions an ...
Qwen3-30B-A3B-MoE-SAE: 80GB+ VRAM
ByteDance-Seed has released Sparse AutoEncoders (SAE) for the Qwen3-30B-A3B model, designed to interpret MoE expert b ...