RND1 is an experimental diffusion language model with 30 billion parameters, adopting a sparse mixture of experts architecture. This model is converted from a pre-trained autoregressive base model, supporting diffusion-based text generation. Only 3 billion parameters are activated for each token, achieving a balance between computational efficiency and model capacity.

Natural Language ProcessingTransformers

CoDA is a code generation language model based on diffusion models developed by Salesforce AI Research. It has the ability to understand bidirectional context and is specifically designed for powerful code generation and completion tasks. This model only has 1.7 billion parameters and achieves excellent code generation performance while maintaining low computational requirements.

Natural Language ProcessingTransformersEnglish

LLaDA-MoE is a new type of mixture-of-experts language model constructed based on the diffusion principle. It is the first open-source MoE diffusion large language model, pre-trained from scratch on approximately 20 trillion tokens. It has a total of 7 billion parameters, and only 1.4 billion parameters are activated during inference. It performs excellently in tasks such as code generation and mathematical reasoning.

Natural Language ProcessingTransformers

SDAR is a new type of large language model that integrates autoregressive and discrete diffusion modeling strategies, combining the advantages of efficient training of AR models and parallel inference of diffusion models. It performs comparably to SOTA open - source AR models on general tasks and excels in scientific reasoning tasks, becoming the most powerful diffusion language model.

Natural Language ProcessingTransformers

SongBloom is an innovative full-length song generation framework that adopts an interleaved paradigm of autoregressive sketch drawing and diffusion-based refinement, combining the high fidelity of diffusion models and the scalability of language models to generate high-quality full-length songs.

Dream-Coder-v0-Base-7B is an open-source, top-performing large language model for code generation diffusion, focusing on code generation tasks.

Natural Language ProcessingTransformers

LLaDA 1.5 is a large diffusion language model trained using the Variance Reduction Preference Optimization (VRPO) method, focusing on improving the quality and efficiency of text generation.

Natural Language ProcessingTransformers

LLaDA-V is a vision-language model based on the diffusion model, outperforming other diffusion multimodal large language models in performance.

MultimodalSafetensors

Dimple is the first discrete diffusion multimodal large language model (DMLLM) that combines autoregressive and diffusion training paradigms. After training on the same dataset as LLaVA-NEXT, it outperforms LLaVA-NEXT-7B by 3.9%.

MultimodalTransformersEnglish

An experimental natural language to 3D model generation pipeline based on an improved pre-trained multi-view diffusion model

MultimodalDiffusers

Nexus-Gen is a unified model that combines the linguistic reasoning capabilities of large language models with the image generation capabilities of diffusion models

MultimodalTransformers

SkyReels V2 is the world's first unlimited-length cinematic generation model employing a diffusion-forcing framework, integrating multimodal large language models, multi-stage pretraining, reinforcement learning, and diffusion-forcing technology for comprehensive optimization.

MultimodalDiffusers

AudioX is a unified diffusion transformer model capable of generating audio and music from arbitrary content. It produces high-quality general audio and musical compositions, offers flexible natural language control, and seamlessly handles multimodal inputs.

A diffusion-based text-to-image model supporting natural language and native tag input, utilizing v-prediction mechanism

Computer VisionDiffusersMultiple Languages

BD3-LMs is a language model that combines the advantages of autoregressive and diffusion models, achieving efficient sequence generation through block discrete diffusion.

Natural Language ProcessingTransformers

BD3-LMs is a language model that combines the strengths of autoregressive and diffusion models, achieving efficient sequence generation through block discrete diffusion.

Natural Language ProcessingTransformers

BD3-LMs is a language model that combines the advantages of autoregressive and diffusion models, achieving efficient sequence generation through block discrete diffusion

Natural Language ProcessingTransformers

Illustrious XL v1.0 is a high-resolution professional illustration generation model based on the Stable Diffusion XL architecture, supporting native 1536×1536 resolution and integrating natural language with tag prompt systems.

Computer VisionDiffusers

BigAsp is a text-to-image generation model based on Stable Diffusion XL. It supports natural language prompts and booru-style tags, has diverse generation capabilities, and is particularly good at generating realistic and lifelike images, performing excellently on specific themes such as ponies.

MultimodalDiffusersEnglish

Diffusion language model fine-tuned based on Llama-2-7b

Natural Language ProcessingTransformers