pollockjj / ComfyUI-MultiGPULinks
This custom_node for ComfyUI adds one-click "Virtual VRAM" for any GGUF UNet and CLIP loader, managing the offload of layers to DRAM or VRAM to maximize the latent space of your card. Also includes nodes for directly loading entire components (UNet, CLIP, VAE) onto the device you choose. Includes 16 examples covering common use cases.
☆320Updated 2 months ago
Alternatives and similar repositories for ComfyUI-MultiGPU
Users that are interested in ComfyUI-MultiGPU are comparing it to the libraries listed below
Sorting:
- ☆410Updated 2 months ago
- Rudimentary support for using multiple GPUs in a ComfyUI workflow☆266Updated 10 months ago
- Quick Connections for ComfyUI & litegraph☆282Updated 2 months ago
- ☆330Updated 4 months ago
- If your image was a pizza and the CFG the temperature of your oven: this is a thermostat that ensures it is always cooked like you want. …☆413Updated 9 months ago
- An implementation of Depthflow in ComfyUI☆284Updated this week
- Custom Conditioning Delta (ConDelta) nodes for ComfyUI☆200Updated 2 months ago
- This extension serves as a complement to the Impact Pack, offering features that are not deemed suitable for inclusion by default in the …☆210Updated last week
- LoRA Manager for ComfyUI - A powerful extension for organizing, previewing, and integrating LoRA models with metadata and workflow suppor…☆316Updated this week
- ☆351Updated 5 months ago
- Run ComfyUI workflows on multiple local GPUs/networked machines.☆455Updated last year
- ☆322Updated last month
- A modular workflow for FLUX inside of ComfyUI that brings order to the chaos of image generation pipelines.☆193Updated this week
- ComfyUI wrapper for InvSR (Arbitrary-steps Image Super-resolution via Diffusion Inversion)☆210Updated last month
- ComfyUI nodes to crop before sampling and stitch back after sampling that speed up inpainting☆728Updated last month
- ☆255Updated this week
- ☆241Updated 6 months ago
- ComfyUI Wrapper for HiDream☆478Updated 2 months ago
- A powerful anti-burn allowing much higher CFG scales for latent diffusion models (for ComfyUI)☆195Updated 8 months ago
- Compositor Node experiments☆457Updated last month
- Attention Couple, NegPip (negative weights in prompts) for SDXL, FLUX and HunyuanVideo, more CFG++ and SMEA DY samplers, etc.☆194Updated last week
- ☆270Updated 3 weeks ago
- Support for miscellaneous image models. Currently supports: DiT, PixArt, HunYuanDiT, MiaoBi, and a few VAEs.☆509Updated 6 months ago
- You can InstantIR to upsacel image in ComfyUI ，InstantIR,Blind Image Restoration with Instant Generative Reference☆235Updated 3 months ago
- Flow is a custom node designed to provide a user-friendly interface for ComfyUI.☆547Updated 5 months ago
- ☆589Updated 2 months ago
- 6 nodes for ComfyUI that allows for more control and flexibility over noise to do e.g. variations or "un-sampling"☆298Updated last year
- ComfyUI nodes for prompt editing and LoRA control☆297Updated last week
- A port of muerrilla's sd-webui-Detail-Daemon as a node for ComfyUI, to adjust sigmas that control detail.☆741Updated 3 months ago
- A selection of nodes for Stable Diffusion ComfyUI☆527Updated 3 months ago