H3 Studio is no longer just a one-clip box. Director → Cinema Studio is a short-film desk: you import a text ...
Launcher updates
Phosphene 4.12.3 - One-shot takes stay in sync
Small fix release. If you rendered a One-shot take of more than one part and the voice drifted behind the lip...
TL;DR: If MiniMax H3 in Maestro / WanGP "finishes" a generation but the file is a tiny ( 50 KB) solid-grey cl...
Maestro v2.1 is live!
Maestro v2.1 is live! 🎬 • Viggle Animate Support! • Streamlined UI & Menus • Save & share characters...
theDAW by GANTASMO: everything you've wanted from a DAW, and much more. All for Free!
theDAW is a DJ, and VJ app interoperable w/Ableton, Reaper, Resolume & more. Stable Audio 3, Magenta RT2, Sun...
Store
#ai189#tts58#image-generation44#video-generation39#136#utility34#próba27#video27#music26#3d24#agent24#faceswap22#audio20#image-edit18#audio-generation17#3dgen15#llm15#ui15#voice15#voice-clone15#image13#music-generation13#song-generation13#comfyui12#agents11#pinokio11#ses-klonlama11#song11#training11#generation10
1-click MiniMax H3 video in ComfyUI plus H3 Studio: Director, Plan, cinema studio, TR/EN. NVIDIA GPU.
@mvrdvk
10 check-ins
MiniMax H3 ComfyUIFeatured
MiniMax H3 omni-modal video generation in ComfyUI. Text/image/video/audio in, video with native 32kHz stereo audio out (768p default, 1080p+ supported). Disk-optimized: pruned INT8 + NVFP4 weights (~63GB instead of ~290GB). NVIDIA only.
@thomas_eric
34 check-ins[AMD ONLY] All-in-one local AI video, image & music studio built on the WanGP pipeline (Wan 2.1/2.2, LTX-2.3, Qwen, Hunyuan Video, Flux). ROCm-powered. Supported on Windows and Linux for RDNA 2-4 dGPUs (RX 6000/7000/8000/9000) and gfx1150-53 APUs (Strix Point/Halo, Krackan Point/Halo). 6 GB+ VRAM recommended. For NVIDIA GPUs use the upstream Maestro app. Credits: the app itself is Maestro by Blizaine (github.com/Blizaine/Maestro) — this is just an AMD installer wrapper around it. The clone-at-install-time approach used to port it to AMD was pioneered by 6Morpheus6's wan2gp-amd (github.com/6Morpheus6/wan2gp-amd).
@yoyokits
5 check-ins
Zero-shot multilingual TTS (600+ languages) with voice cloning and voice design — Gradio UI (app/app.py)
Tokenizer-free TTS for context-aware speech, voice cloning, and voice design. 2B params, 48kHz, 30 languages (Gradio UI).
Wan2GP - AMDFeatured
[AMD ONLY] 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, Flux and more. (On Windows supported by all dedicated AMD GPUs from RDNA 2 - RDNA 4)
@morpheus
169 check-ins
e2-f5-ttsFeatured
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching https://huggingface.co/spaces/mrfakename/E2-F5-TTS
29 check-ins
Unsloth StudioFeatured
Run and train AI models with a unified local interface. https://github.com/unslothai/unsloth
@cocktailpeanut
9 check-ins
Z-Image, Flux2 Klein, & SeedVR2 with a Gradio UI. Uses a built-in ComfyUI backend for speed and efficiency! [8GB+VRAM, 16GB+ RAM]
@anchorite
23 check-ins
A lightweight local launcher and control panel for llama.cpp.
Wan2GPFeatured
1-click WanGP Launcher. 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
582 check-ins
VibeVoice RealtimeFeatured
Realtime streaming TTS demo using microsoft/VibeVoice-Realtime-0.5B
A live 3D intelligence console for planet Earth.
Uncensored deepfakes for images and videos, no training required. Advanced masking, batch processing, and face enhancement powered by InsightFace and ONNX. Supports NVIDIA (CUDA/TensorRT), AMD (DirectML/ROCm), Apple Silicon, and CPU.
@adutchguy
9 check-ins
RMBG-2-StudioFeatured
Enhanced background remove and replace app built around BRIA-RMBG-2.0 https://huggingface.co/briaai/RMBG-2.0
Open WebUIFeatured
User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-compatible APIs https://github.com/open-webui/open-webui
32 check-ins