Model Releases: 310 curated resources
Curated material on model releases within frontier.
310 resources · page 9 of 10
Inside Higgsfield #1: How We Built Cinema Studio
Creator not supplied; see original source.
Higgsfield engineering post describing how the team built its Cinema Studio video generation feature.
Ideogram docs
Creator not supplied; see original source.
Ideogram documentation: guides to generating and editing images and video, text and logo workflows, and model comparisons.
Gemini API docs: Image generation
Creator not supplied; see original source.
Gemini API documentation on image generation and editing with the Nano Banana models.
OpenAI API guide: Image generation
Creator not supplied; see original source.
OpenAI API guide to generating and editing images with its image generation models.
Invoke creative workflow documentation
Creator not supplied; see original source.
InvokeAI documentation: open-source creative engine for image generation with canvas workflows and model management.
Releasing Open Weights for FLUX.1 Krea
Creator not supplied; see original source.
Krea post releasing open weights for FLUX.1 Krea, with training details and resources to run and fine-tune it.
Kyutai TTS
Creator not supplied; see original source.
Kyutai text-to-speech page presenting its open TTS model.
Diffusers: Inpainting
Creator not supplied; see original source.
Hugging Face Diffusers guide to inpainting: editing masked regions of images with diffusion models.
Meshy docs
Creator not supplied; see original source.
Meshy documentation: AI 3D model generator from text and images, with guides for games, AR and 3D printing.
Building Shared Memory for AI Agents in Notion
Creator not supplied; see original source.
Notion post on Lore, a system that turns conversations and decisions into Notion pages that agents use as shared memory.
How we built security into Custom Agents (Notion)
Creator not supplied; see original source.
Notion post on the security model of its Custom Agents and what testing at scale showed.
Gamma: How do I create a new presentation, document, or webpage?
Creator not supplied; see original source.
Gamma help article on creating a new AI-generated presentation, document or webpage.
Recraft blog
Creator not supplied; see original source.
Recraft blog with tutorials and examples for creating vector and raster graphics with Recraft's image models.
Recraft docs
Creator not supplied; see original source.
Recraft API documentation: generating and editing raster and vector images with Recraft models over REST.
Replicate docs
Creator not supplied; see original source.
Replicate documentation: running ML models through a cloud API and packaging models with Cog.
Runway API docs
Creator not supplied; see original source.
Runway API documentation for integrating Runway video generation models into applications.
Seedream 4.0 (ByteDance Seed)
Creator not supplied; see original source.
ByteDance Seed page for Seedream 4.0, its image generation and editing model.
Sesame research
Creator not supplied; see original source.
Sesame research post on conversational voice: building speech models with natural voice presence.
Smallest AI Docs: Models overview
Creator not supplied; see original source.
Smallest AI models overview: text-to-speech, speech-to-text, speech-to-speech and LLM models with model cards.
Soniox API reference
Creator not supplied; see original source.
Soniox API reference for speech-to-text and text-to-speech, with OpenAPI spec and streaming protocols.
Stability AI news
Creator not supplied; see original source.
Stability AI news page with model releases and company updates for Stable Diffusion and other models.
Stable Audio
Creator not supplied; see original source.
Stability AI page on Stable Audio 3.0, audio generation models trained on licensed data.
Suno Knowledge Base
Creator not supplied; see original source.
Suno knowledge base: help articles for creating songs with Suno's AI music generator.
Diffusers: Text-to-image
Creator not supplied; see original source.
Hugging Face Diffusers guide to text-to-image generation with code examples.
Veo (Google DeepMind)
Creator not supplied; see original source.
Google DeepMind Veo 3.1 page: video generation model with native audio, controls and example outputs.
ElevenLabs prompting best practices
Creator not supplied; see original source.
ElevenLabs best practices for controlling speech delivery, pronunciation and emotion in text-to-speech.
3D Gaussian Splatting
Creator not supplied; see original source.
arXiv paper (2023) introducing 3D Gaussian Splatting for real-time radiance field rendering.
Alpha3D developer portal
Creator not supplied; see original source.
Alpha3D developer portal: API docs, webhooks and usage tools for its AI 3D generation pipeline.
How Alpha3D works
Creator not supplied; see original source.
Alpha3D post explaining its multi-stage pipeline for generating, retopologising, unwrapping and texturing 3D assets.
DDPM
Creator not supplied; see original source.
arXiv paper (2020) "Denoising Diffusion Probabilistic Models", introducing DDPM image generation by learning to reverse a gradual noising process.
DiT (Scalable Diffusion Transformers)
Creator not supplied; see original source.
arXiv paper (2022) introducing Diffusion Transformers (DiT), scalable diffusion models with transformer backbones.
Essentia
Creator not supplied; see original source.
Essentia documentation: open-source library from UPF for audio and music analysis, with ML models.