A ControlNet PEFT LoRA model based on terminusresearch/auraflow-v0.3 for high-quality text-to-image conversion

Computer VisionDiffusers

VoxPolska Auralis is an advanced Polish text-to-speech (TTS) model that uses cutting-edge deep learning technology to accurately capture the nuances and intonations of the Polish language, converting written text into natural, fluent, and expressive speech.

Audio ProcessingTransformersOther

Aurora-1.6B is a multilingual emotional and singing speech synthesis model fine-tuned based on Dia-1.6B, supporting multiple languages and emotional control with zero-shot voice cloning capability.

Audio ProcessingSafetensorsMultiple Languages

A multilingual emotional and singing voice synthesis model fine-tuned based on Dia-1.6B, supporting voice cloning and emotion control

AuriStream-1B is a biologically inspired GPT-style autoregressive Transformer model specifically designed to predict cochlear markers in long speech contexts. The model uses a long context window of approximately 20 seconds (4096 tokens) and was trained on the LibriLight dataset (approximately 60,000 hours) for about 500,000 steps. It can learn rich time-aligned representations and generate speech continuations.

Audio ProcessingTransformersEnglish

This is an experimental multi-model fusion project based on the LLaMa-70B architecture, utilizing the DARE TIES fusion method and combining six different versions of the MO-MODEL.

Natural Language ProcessingTransformers

A standard PEFT LoRA model trained on fal/AuraFlow, specializing in text-to-image and image-to-image generation tasks for Domo-kun characters.

Computer VisionDiffusers

AuraFlow v0.3 is a fully open-source flow-based text-to-image generation model that supports multiple aspect ratios, with resolutions up to 1536 pixels.

MultimodalDiffusers

This model uses an improved vnet architecture for image-to-image processing, supporting tasks such as adversarial, aesthetic, and quality enhancement

Computer VisionTensorflow

This model employs an improved VNet architecture for 2D image processing, focusing on image-to-image translation tasks with adversarial and aesthetic optimization features.

Computer VisionTensorflow

A multilingual ChatML model merged using the SCE method, supporting English and Japanese dialogue

Natural Language ProcessingTransformersMultiple Languages

A text-to-image generation model based on fal/AuraFlow-v0.3, offering GGUF quantized and FP8 scaled versions, suitable for ComfyUI environments.

Computer VisionGgufEnglish

This is a direct GGUF format conversion of fal/AuraFlow-v0.3, primarily used for text-to-image generation tasks.

MultimodalGguf

Aura-4B is a quantized version based on AuraIndustries/Aura-4B, using llama.cpp for imatrix quantization, supporting multiple quantization types, suitable for text generation tasks.

Natural Language ProcessingGgufEnglish

AuroraCap is a multimodal large language model for image and video captioning, focusing on efficient and detailed video caption generation.

MultimodalSafetensors

AuraFlow v0.3 is a fully open-source flow-based text-to-image generation model that supports multiple aspect ratios, with resolutions up to 1536 pixels.

MultimodalDiffusers

Mistral Nemo 12B Starsong is an experimental model obtained by merging pre-trained language models using the TIES method with the mergekit tool. It is merged based on the two models MN-12B-Celeste-V1.9 and MN-12B-Lyra-v1, and performs well in handling security content.

Natural Language ProcessingTransformers

GAN-based super-resolution technology for enhancing the quality of generated images

Computer VisionTransformersOther

AuraFlow v0.2 is a fully open-source, largest flow-based text-to-image generation model, achieving state-of-the-art results in the GenEval benchmark.

Computer VisionDiffusers

AuraFlow v0.1 is a fully open-source, largest-scale flow-based text-to-image generation system, achieving state-of-the-art results on the GenEval benchmark.

MultimodalDiffusers