Hy3
Try Hy3 online Demo. Hy3 is Tencent’s open 295B MoE model with 21B active parameters, 256K context, Apache 2.0 license, and agent-focused features.
Try This Model NowTry Hy3 online Demo. Hy3 is Tencent’s open 295B MoE model with 21B active parameters, 256K context, Apache 2.0 license, and agent-focused features.
Try This Model NowOrnith is an open-source AI coding model family from DeepReinforce. Learn what it does, model sizes, license, features, and use cases.
Try This Model NowBoogu is an Apache-2.0 image generation and editing model family with text-to-image, fast Turbo, fp8, and editing variants.
Try This Model NowVoxCPM 2 is an open-source TTS model for multilingual speech, voice design, cloning, and 48kHz audio. See features, setup, and limits.
Try This Model NowIdeogram 4 is an open-weight text-to-image model with JSON prompts, strong text rendering, 2K output, and API access for teams.
Try This Model NowMiniMax M3 is an open-weight multimodal AI model with 1M context, sparse attention, coding strengths, API access, and local deployment.
Try This Model NowUse this Lofi Dusk prompt to turn a normal selfie or portrait into a moody Instagram-style photo with soft flash, glowing rim light, dark background, film grain, and cinematic dusk colors.
Want to turn your photo into a World Cup-style football sticker? Use these Figurinha da Copa prompts to create a custom player card with AI.
Copy and paste CG City Tour prompts for ChatGPT, Gemini, and AI photo editing. Create realistic city travel photos, DP images, couple portraits, and Instagram-style edits.
Cosmos 3 is NVIDIA’s open world foundation model for robotics, autonomous vehicles, smart spaces, and physical AI simulation.