Unified Model Catalog

Extend the beginning or end of provided audio with lyrics and/or style using ACE-Step

Modify a portion of provided audio with lyrics and/or style using ACE-Step

Generate music from a lyrics and example audio using ACE-Step

Generate music from a simple prompt using ACE-Step

Generate music with lyrics from text using ACE-Step

Modify a face to look younger or older while keeping identity realistic.

MultiTalk model generates a talking avatar video from an image and text. Converts text to speech automatically, then generates the avatar speaking with lip-sync.

MultiTalk model generates a talking avatar video from an image and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.

MultiTalk model generates a multi-person conversation video from an image and text inputs. Converts text to speech for each person, generating a realistic conversation scene.

MultiTalk model generates a multi-person conversation video from an image and audio files. Creates a realistic scene where multiple people speak in sequence.

Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with a 256K context window,…

Jamba Mini 1.7 is a compact and efficient member of the Jamba open model family, incorporating key improvements in grounding and instruction-following while maintaining the benefits of the SSM-Transformer hybrid archite…

Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It is built on DeepSeek-R1, augmented with additional models and techniques such as Tree of Thoughts (…

Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic. It is a modified variant of a FuseAI model…

Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned…

A finetuned 7 billion parameters Code LLaMA - Instruct model to generate Solidity smart contract using 4-bit QLoRA finetuning provided by PEFT library.

OLMo-2 32B Instruct is a supervised instruction-finetuned variant of the OLMo-2 32B March 2025 base model. It excels in complex reasoning and instruction-following tasks across diverse benchmarks such as GSM8K, MATH, IF…

Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding eva…

Olmo 3 7B Instruct is a supervised instruction-fine-tuned variant of the Olmo 3 7B base model, optimized for instruction-following, question-answering, and natural conversational dialogue. By leveraging high-quality ins…

Olmo 3 7B Think is a research-oriented language model in the Olmo family designed for advanced reasoning and instruction-driven tasks. It excels at multi-step problem solving, logical inference, and maintaining coherent…

Olmo 3.1 32B Think is a large-scale, 32-billion-parameter model designed for deep reasoning, complex multi-step logic, and advanced instruction following. Building on the Olmo 3 series, version 3.1 delivers refined reas…

Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing documents, extracting…

Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time customer interactions,…

Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length of 128K tokens and optimized for speed and cost, Amazon…

Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.

Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the-art performance on k…

Interpolate between image frames

Interpolate between video frames

Animate your ideas!

Re-animate your videos!

Animate Your Drawings with Latent Consistency Models!

Animate your ideas in lightning speed!

Re-animate your videos in lightning speed!

Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https://www.anthropic.com/n…

Claude 3 Opus is Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding. See the launch announcement and benchmark results [here](https://www.…

Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such a…