heatdrop.ai

A curated prompt cookbook for OpenAI's latest image model, covering portraits, UI mockups, game screenshots, and posters you can drop straight into the API.

VoxCPM2 generates speech directly from text using continuous diffusion, no discrete audio tokens required.

Cosmos 3 tries to unify video generation, robot action prediction, and physical reasoning inside a single 16B–64B Mixture-of-Transformers architecture.

ViMax orchestrates director, screenwriter, and producer agents to generate multi-shot videos from raw ideas, novels, or scripts.

An Electron app that wraps 200+ generative models behind a single UI, with an unusual pitch: no guardrails, no cloud lock-in, and a split personality between local and remote inference.

A Chinese speech toolkit that bundles ASR, diarization, emotion detection, and streaming into one MIT-licensed package.

Voice-Pro bundles Whisper, F5-TTS, CosyVoice, and a dozen other tools into a single Gradio interface for creators who want ElevenLabs-like results without the API bills.

OpenAI's Whisper replaces the usual Rube Goldberg pipeline of speech-processing tools with a single Transformer trained to do it all.

A foundation model that turns one image into a full 3D body mesh, optionally guided by keypoints or masks like the original SAM.

A fully offline speech toolkit packing ASR, TTS, diarization, and VAD into one C++ runtime with ONNX, then wrapping it for twelve languages and every edge platform imaginable.

A speed-focused deep learning system for analyzing massive scientific images, from crowds to cancer slides to galaxies.

VideoClaw turns a one-sentence prompt into a full production pipeline with editable checkpoints, not just a black-box video dump.

Structured prompt packs that let Claude Code or Cursor generate, edit, and display images, video, and audio via a unified CLI backend.

MLX-VLM crams speculative decoding, continuous batching, and KV cache quantization into a Mac-native toolkit for running multimodal models locally.

BiRefNet splits images into layers using bilateral references, then offers a whole zoo of task-specific weights for everything from background removal to camouflaged-object detection.

A grab-bag node pack whose Set/Get rewrite might finally tame your worst workflow tangles.

A foundation model that turns prompts into game-ready meshes, because someone finally had to do it for the metaverse.

A free add-on that turns Blender's Video Sequence Editor into an end-to-end AI movie pipeline, from script to screen and back again.

Extends 3D Gaussian Splatting to time-varying scenes without sacrificing the real-time rendering speed that made the original technique appealing.

OpenWhispr is the open-source, privacy-first alternative to WisprFlow and Granola that lets you choose between local Whisper/Parakeet models or your own cloud API keys.