The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Commits on master
Update README.md for Intel Arc GPU installation, remove IPEX (#10729)
e1d85e7 Qiacheng Li committed 1 year ago
Don't pin tensor if not a torch.nn.parameter.Parameter (#10718)
1199411 comfyanonymous committed 1 year ago
Update CI workflow to remove dead macOS runner. (#10704)
5ebcab3 comfyanonymous committed 1 year ago
Unload weights if vram usage goes up between runs. (#10690)
dea899f comfyanonymous committed 1 year ago
Tell users they need to upload their logs in bug reports. (#10671)
eb1c42f comfyanonymous committed 1 year ago
feat(API-nodes): move Rodin3D nodes to new client; removed old api client.py (#10645)
bda0eb2 Alexander Piskun committed 1 year ago
Lower ltxv mem usage to what it was before previous pr. (#10643)
c4a6b38 comfyanonymous committed 1 year ago
Limit amount of pinned memory on windows to prevent issues. (#10638)
7f3e4d4 comfyanonymous committed 1 year ago
This seems to slow things down slightly on Linux. (#10624)
0f4ef3a comfyanonymous committed 1 year ago
Bring back fp8 torch compile performance to what it should be. (#10622)
6b88478 comfyanonymous committed 1 year ago