@morpheus

🎙️ Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning. High-quality text-to-speech synthesis supporting zero-shot voice cloning and streaming inference with natural emotional expression.

Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.

[NVIDIA Only] Dead simple web UI for training FLUX LoRA with LOW VRAM support (From 12GB)

When Expressive Talking Head Generation Meets Diffusion Probabilistic Models (https://github.com/ali-vilab/dreamtalk)

Local-first voice synthesis studio powered by Qwen3-TTS.

[NVIDIA, ROCM] One app to train them all. LORA training and Model finetuning for Z-Image, Qwen Image, FLUX.1, Flux.2 Dev and Klein, Chroma, SD 1.5 - 3.5, SDXL, Würstchen-v2, Stable Cascade, PixArt-Alpha, PixArt-Sigma, Sana, Hunyuan Video and inpainting models.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. https://github.com/comfyanonymous/ComfyUI

Sandboxed LM Studio-only OpenClaw fork packaged for Pinokio.

Distill and quantize models using TorchAO with intelligent GPU/CPU management

[NVIDIA ONLY] A minimal Gradio interface for Automatic Speech Recognition. Transcribe Audio in Malayalam language.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. https://github.com/comfyanonymous/ComfyUI

Prebuilt DeepSpeed wheels for Windows with NVIDIA GPU support. Supports GTX 10 - RTX 50 series. Compiled with pytorch 2.7, 2.8 and cuda 12.8

Super Optimized Gradio UI for AI video creation for GPU poor machines (6GB+ VRAM). Supports Wan 2.1/2.2, Qwen, Hunyuan Video, LTX Video and Flux. https://github.com/deepbeepmeep/Wan2GP

clone voices into different languages by using just a quick 3-second audio clip. (a local version of https://huggingface.co/spaces/coqui/xtts)

🦙 Let 2 models debate about a topic you pick. Create custom Ollama models with your own system prompts and parameters and use them to debate ot publish on ollama.com Easy-to-use Gradio interface for building personalized AI models with temperature control and custom instructions.

Improve your audio quality with AI-powered upscaling using NovaSR.

Pinokio wrapper: installs HeartMuLa heartlib + downloads checkpoints + launches a Gradio UI for music generation.

User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-compatible APIs https://github.com/open-webui/open-webui

AuraSR-v2 - An open reproduction of the GigaGAN Upscaler from fal.ai https://huggingface.co/spaces/gokaygokay/AuraSR-v2

One-click installer for Microsoft TRELLIS.2: High-quality 3D asset generation from images with PBR textures.