You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
WeeLLM runs large diffusion models with as little as 4 GB of VRAM, without any quantization. It dynamically determines how many layers can fit within the available VRAM and streams the text encoder and transformer layers to the GPU layer by layer, enabling inference on hardware with limited VRAM. It supports both safetensors and GGUF models.
SunnyChuxemLoRAv2 is the newest version of the open-source commercial benchmarking character model for TrenchPetals Sunny Chuxem. Trained natively on Stable Diffusion 3.5 Large to flawlessly convert primitive MS Paint concept art into high-fidelity production assets!
SuperklokStyleLoRAv2 is the newest version of the open-source commercial benchmarking style model that captures the Superklok art style's retro tech aesthetic. Trained natively on SD 3.5 Large to flawlessly apply ultra-saturated, neon-green circuit board textures, authentic analog CRT monitor scanlines, and high-fidelity branding onto your imagery!
SuperklokStyleLoRA is the ultimate open-source commercial benchmarking style model that captures the Superklok art style's retro tech aesthetic. Trained natively on Stable Diffusion 3.5 Large to flawlessly apply ultra-saturated, neon-green circuit board textures, authentic analog CRT monitor scanlines, and high-fidelity branding onto your imagery!
SunnyChuxemLoRA is the ultimate open-source commercial benchmarking character model for TrenchPetals Sunny Chuxem. Trained natively on Stable Diffusion 3.5 Large to flawlessly convert primitive MS Paint concept art into high-fidelity production assets!
A powerful and flexible custom node pack for ComfyUI, designed to eliminate boilerplate and keep your workflows clean and focused. From model loading to post-production — everything you need in one place.