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
Fix quantized text encoder matmul gating and Gemma4 prefill cache positions (#16185)
b7ebfd7 Jukka Seppänen committed 2 months ago
feat: Pixal3D multiview model support (CORE-421) (#16048)
488e8f8 Jukka Seppänen committed 2 months ago
Add LTXV generated-keyframe nodes and Freeze Latent (#16040)
efa6c8f Adam Oster committed 2 months ago
Verify aotriton kernels actually launch before enabling pytorch attention (#15648)
41db8f4 DELUXA committed 2 months ago
Disable int8 weight-only quantization on devices without torch._int_mm (fixes MPS crash) (#16130)
313a76f Jialong(Bruce) Li committed 2 months ago
Don't invert the alpha channel in the Invert Image node (#15622)
fbed745 Christian Byrne committed 2 months ago
Don't blend the alpha channel in the Blend Images node (#15625)
f9c706f Christian Byrne committed 2 months ago
Fix Draw Text Overlay on images with an alpha channel (#15634)
20f1a41 Christian Byrne committed 2 months ago
Fix Quantize Image on images with an alpha channel (#15630)
aa4582f Christian Byrne committed 2 months ago
Don't adjust the alpha channel in the image color adjustment nodes (#15629)
25dfc16 Christian Byrne committed 2 months ago
Fix Detect Edges (Canny) on images with an alpha channel (#15631)
d03a243 Christian Byrne committed 2 months ago
Fix the RGB/YUV conversion nodes on images with an alpha channel (#15632)
07dd46d Christian Byrne committed 2 months ago
Fix test_base_path_changes leaking a reloaded cli_args singleton (#16053)
82db403 guill committed 2 months ago
Pause comfy compiler for long lived sparse allocations (#16148)
a99d1f9 rattus committed 2 months ago
Fix potential mps issue of supports_fp64 called with None. (#16136)
d1c5e64 comfyanonymous committed 2 months ago
[Partner Nodes] feat(OpenAI): add gpt 6 astra model and reasoning param (#16125)
8a43c6b Alexander Piskun committed 2 months ago
[Partner Nodes] feat(Comfy-Cloud): add nodes that run curated workflows on Comfy Cloud GPUs (#15935)
250b2e9 Deep Mehta committed 2 months ago