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
feat: per-guide attention strength control in self-attention (#12518)
a452201 Tavi Halperin committed 8 months ago
Fix KeyError when prompt entries lack class_type key (#12595)
33f83d5 Jedrzej Kosinski committed 8 months ago
Don't crash right away if op is uninitialized. (#12615)
599f9c5 comfyanonymous committed 8 months ago
feat(api-nodes): add ByteDance Seedream-5 model (#12609)
d809001 Alexander Piskun committed 8 months ago
Temporality unbreak some LTXAV workflows to give people time to migrate. (#12605)
84aba95 comfyanonymous committed 8 months ago
Add SplitImageToTileList and ImageMergeTileList nodes. (#12599)
9b1c63e comfyanonymous committed 8 months ago
Move LTXAV av embedding connectors to diffusion model. (#12569)
f266b8d comfyanonymous committed 9 months ago
chore: tune CodeRabbit config to limit review scope and disable for drafts (#12567)
b6cb30b Christian Byrne committed 9 months ago
Add category to Normalized Attention Guidance node (#12565)
ee72752 Christian Byrne committed 9 months ago
fix: specify UTF-8 encoding when reading subgraph files (#12563)
7591d78 Alexander Brown committed 9 months ago
comfy-aimdo 0.2 - Improved pytorch allocator integration (#12557)
0bfb936 rattus committed 9 months ago
add support for pyopengl < 3.1.4 where the size parameter does not exist (#12555)
602b250 pythongosssss committed 9 months ago
fix: swap essentials_category from CLIPTextEncode to PrimitiveStringMultiline (#12553)
04a55d5 Christian Byrne committed 9 months ago