@morpheus

4 posts62 checkpointsJoined 1/20/2026, 8:49:49 PM

@6morpheus6

Activity 66 Posts 4 Checkpoints 62 Apps 18 Creations 65 Following 11 Followers 303

Posts by @morpheus

4 total

Post3/2/2026, 6:01:56 PM

@morpheusposted inWan2GP

Unified WAN2GP installer for NVIDIA and AMD with python 3.11, pytorch 2.10 and NVFP4 support

11 comments

The latest update combines the WAN2GP installer with the WAN2GP-AMD installer. It is compatible with GTX10 - RTX50 seri…

Post2/25/2026, 6:11:06 AM

@morpheusposted inSide-Step

Train AceStep LoRAs with only 8GB VRAM

3 comments

You want to train AceStep LoRAs but don't have the hardware to do it in Ace-Step 1.5, Side-Step might be the right tool…

Post1/25/2026, 6:37:30 AM

@morpheusposted inLivePortrait

Fixed Animal Mode for RTX50

3 comments

#img2video #lipsync

I just fixed the Animal Mode in Liveportrait for RTX50 series. Who ever couldn't make it work, just update Liveportrait…

Post1/21/2026, 10:38:09 PM

@morpheusposted inHeartMuLa (HeartMuLaGen)

Amazing song quality with HeartMuLa

4 comments

#audio #heartmula #heartmulagen #music #song #songgeneration

HeartMuLa has the best quality of all song generation apps I've tried so far. This is more than you'd expected from an …

Creations

More · 65

Onetrainer

[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.Updated 2 hours ago

Wan2GP

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/Wan2GPUpdated 3 days ago

Forge Neo

[NVIDIA ONLY] Stable Diffusion WebUI Forge supporting Flux, Qwen, wan, nunchaku and more in a lightweight WebUI. https://github.com/Haoming02/sd-webui-forge-classic/tree/neoUpdated last week

Comfyui

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

SoraWatermarkCleaner

Automatically remove watermarks from videos generated by Sora AI.Updated last week

RamClaw

Sandboxed LM Studio-only OpenClaw fork packaged for Pinokio.Updated 2 weeks ago

SongGeneration

Generate music in different genres using text and audio prompts.Updated 2 weeks ago

QTinker

Distill and quantize models using TorchAO with intelligent GPU/CPU managementUpdated 3 weeks ago

Fooocus

Minimal Stable Diffusion UIUpdated 3 weeks ago

Side-Step

Optimized Training script for Ace-Step with low VRAM support for local GPUs.Updated 4 weeks ago