Downloads · 30 days
0
forge-vram-offload-optimizer
TediumDispenser/forge-vram-offload-optimizer
forge-vram-offload-optimizer is a machine learning model from TediumDispenser. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Working with Flux models on Forge with low VRAM GPUs inevitably leads to out of memory crashes when changing models frequently as residual data does not get fully cleared, eventually leading to VRAM saturation. The tr…
Access
Public
Updated Mar 15, 2025
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.md2.2 KB · 48%
At a glance
- License
- mit
- Access
- Public
- Created
- Mar 15, 2025
- Updated
- Mar 15, 2025
- SHA
- 3e11aa5b
Model card
From the Hugging Face model README
Forge VRAM Offload Optimizer
Working with Flux models on Forge with low VRAM GPUs inevitably leads to out of memory crashes when changing models frequently as residual data does not get fully cleared, eventually leading to VRAM saturation. The traditional fix has been to add the --always-offload-from-vram launch argument. This results in unloading after every render, making larger models like Flux tedious to work with as unloading/reloading takes up significant time.
What FVOO does:
Optimizes VRAM usage in Forge by eliminating delays from --always-offload-from-vram between same-model renders by only clearing VRAM when a new model is selected in WebUI. Out of memory crashes are virtually eliminated and time between renders, especially with Flux models is greatly decreased.
Installation
- Place
custom_offload.pyin<forge_root>\scripts\. - Remove
--always-offload-from-vramfrom launch args - Run Forge!
Note: not tested on reForge or A1111 but likely works on those platforms as well
- License
- mit
- Created
- Mar 15, 2025
- Updated
- Mar 15, 2025