"sgl-router/src/routers/vscode:/vscode.git/clone" did not exist on "acc2327bbdf0de19d0dad3c1e4ee47d4df0fb861"
- 14 Jul, 2024 1 commit
-
-
comfyanonymous authored
-
- 09 Jul, 2024 1 commit
-
-
comfyanonymous authored
This is only the model code itself, it currently defaults to an empty embedding [0] * 6 which seems to work better than treating it like a regular controlnet. TODO: Add nodes to select the image type.
-
- 27 Jun, 2024 3 commits
-
-
comfyanonymous authored
-
comfyanonymous authored
Still missing the node to properly use it.
-
comfyanonymous authored
-
- 06 Apr, 2024 1 commit
-
-
comfyanonymous authored
-
- 14 Mar, 2024 1 commit
-
-
comfyanonymous authored
-
- 11 Mar, 2024 1 commit
-
-
comfyanonymous authored
Logging level now defaults to info. --verbose sets it to debug.
-
- 10 Mar, 2024 1 commit
-
-
comfyanonymous authored
-
- 07 Mar, 2024 1 commit
-
-
comfyanonymous authored
-
- 06 Mar, 2024 2 commits
-
-
comfyanonymous authored
-
comfyanonymous authored
-
- 05 Mar, 2024 1 commit
-
-
comfyanonymous authored
-
- 02 Mar, 2024 1 commit
-
-
comfyanonymous authored
The old set_attr has been renamed to set_attr_param.
-
- 16 Feb, 2024 1 commit
-
-
comfyanonymous authored
-
- 09 Feb, 2024 1 commit
-
-
comfyanonymous authored
-
- 22 Jan, 2024 1 commit
-
-
comfyanonymous authored
-
- 10 Jan, 2024 1 commit
-
-
comfyanonymous authored
-
- 22 Dec, 2023 1 commit
-
-
comfyanonymous authored
Let me know if this breaks anything.
-
- 12 Dec, 2023 2 commits
-
-
comfyanonymous authored
-
comfyanonymous authored
comfy.ops -> comfy.ops.disable_weight_init This should make it more clear what they actually do. Some unused code has also been removed.
-
- 04 Dec, 2023 3 commits
-
-
comfyanonymous authored
-
comfyanonymous authored
--fp8_e4m3fn-unet and --fp8_e5m2-unet are the two different formats supported by pytorch.
-
comfyanonymous authored
-
- 16 Nov, 2023 1 commit
-
-
comfyanonymous authored
This doesn't affect how percentages behave in the frontend but breaks things if you relied on them in the backend. percent_to_sigma goes from 0 to 1.0 instead of 1.0 to 0 for less confusion. Make percent 0 return an extremely large sigma and percent 1.0 return a zero one to fix imprecision.
-
- 01 Nov, 2023 1 commit
-
-
comfyanonymous authored
-
- 25 Oct, 2023 1 commit
-
-
Jedrzej Kosinski authored
-
- 22 Oct, 2023 1 commit
-
-
comfyanonymous authored
-
- 13 Oct, 2023 1 commit
-
-
comfyanonymous authored
-
- 23 Sep, 2023 1 commit
-
-
comfyanonymous authored
-
- 08 Sep, 2023 1 commit
-
-
comfyanonymous authored
-
- 01 Sep, 2023 1 commit
-
-
comfyanonymous authored
-
- 31 Aug, 2023 1 commit
-
-
comfyanonymous authored
-
- 29 Aug, 2023 1 commit
-
-
comfyanonymous authored
-
- 28 Aug, 2023 2 commits
-
-
comfyanonymous authored
-
comfyanonymous authored
-
- 26 Aug, 2023 1 commit
-
-
comfyanonymous authored
-
- 25 Aug, 2023 1 commit
-
-
comfyanonymous authored
-