19 Commits (02ca1c67f87e46e926aba325e73b2845d5244874)

Author SHA1 Message Date
comfyanonymous 02ca1c67f8 Don't print traceback when processing interrupted. 2 years ago
comfyanonymous 3a1f9dba20 If IS_CHANGED returns exception delete the output instead of crashing. 2 years ago
comfyanonymous 951c0c2bbe Don't keep cached outputs for removed nodes. 2 years ago
comfyanonymous 0ac319fd81 Don't delete all outputs when execution gets interrupted. 2 years ago
comfyanonymous ccad603b2e Add a way for nodes to validate their own inputs. 2 years ago
ltdrdata f7a8218814
Add clipspace feature. (#541) 2 years ago
comfyanonymous deb2b93e79 Move code to empty gpu cache to model_management.py 2 years ago
藍+85CD d63705d919 Support releases all unoccupied cached memory from XPU 2 years ago
pythongosssss 6f72c4c6ff Allows nodes to return ui data and output data 2 years ago
Davemane42 1e0f2b232b add unique_id to nodes hidden inputs 2 years ago
comfyanonymous bb1223d83f Fix errors appearing more than once. 2 years ago
comfyanonymous 3444ffff3b Fix IS_CHANGED not working on nodes with an input from another node. 2 years ago
comfyanonymous f67c00622f Use inference_mode instead of no_grad. 2 years ago
pythongosssss 5c55c93367 Updated to reuse session id if available 2 years ago
comfyanonymous c8ce599a8f Add a button to interrupt processing to the ui. 2 years ago
comfyanonymous 69cc75fbf8 Add a way to interrupt current processing in the backend. 2 years ago
comfyanonymous 5f0f97634f Only clear cuda cache on CUDA since it causes slowdowns on ROCm. 2 years ago
comfyanonymous cd85f876f2 Try to clear more memory at the end of each prompt execution. 2 years ago
comfyanonymous 49d2e5bb5a Move some stuff from main.py to execution.py 2 years ago
comfyanonymous c0fb0c848f Update colab notebook. 2 years ago
comfyanonymous 6de6246dd4 Fix some potential issues related to threads. 2 years ago
pythongosssss 9f391ab656
changed to store history by uniqueid 2 years ago
pythongosssss 5c5725dac0
Remove extra args 2 years ago
pythongosssss 9bd7bfa648
Added workflow history 2 years ago
pythongosssss a52aa9f4b5
Moved api out to server 2 years ago
comfyanonymous 5f375f0d16 Remove my "deleted" debug print that confused people. 2 years ago
masterpiecebestquality 3a83da7281 empty cache after execute() 2 years ago
comfyanonymous a38a30cb87 Document --highvram and enable it in colab. 2 years ago
pythongosssss 0787299610
Hide Triton warning on Windows 2 years ago
pythongosssss 68a1ac7746
Remove catch that was causing linux ctrl+c issues 2 years ago
pythongosssss 8e51af6786
Changed to serve index.html on root 2 years ago
pythongosssss f616dcc81a
Added handling of missing aiohttp module 2 years ago
pythongosssss 5d14e9b959
Changed HTTP Server + Added WebSockets 2 years ago
comfyanonymous 7e1e193f39 Automatically enable lowvram mode if vram is less than 4GB. 2 years ago
comfyanonymous 534736b924 Add some low vram modes: --lowvram and --novram 2 years ago
comfyanonymous e3e65947f2 Add a --help to main.py 2 years ago
comfyanonymous 1f18221e17 Add --port to set custom port. 2 years ago
comfyanonymous 3f3d77a324 Fix image node always executing instead of only when the image changed. 2 years ago
comfyanonymous 43c795f462 Add a --listen argument to listen on 0.0.0.0 2 years ago
comfyanonymous 4b08314257 Add more features to the backend queue code. 2 years ago
comfyanonymous 3661e10648 Add a command line option to disable upcasting in some cross attention ops. 2 years ago
comfyanonymous bc475f86c4 Slightly better errors. 2 years ago
comfyanonymous eb85896b73 Add code for categories. 2 years ago
comfyanonymous b9308407b2 Make webui return correct mimetypes for css and js files. 2 years ago
comfyanonymous a37261bb4b Try to execute the outputs that take the less steps first. 2 years ago
comfyanonymous 9baa48cb33 Add IS_CHANGED method to nodes to check if nodes should be executed again. 2 years ago
comfyanonymous 220afe3310 Initial commit. 2 years ago