"comfy/ldm/modules/vscode:/vscode.git/clone" did not exist on "83f23f82b8a4ac041dd8262ee12951ac6826162f"
- 11 Jan, 2024 3 commits
-
-
TFWol authored
- Implemented a `try-except` block in the `recursive_search` function to handle `FileNotFoundError` gracefully. - When encountering a file or directory path that cannot be accessed (causing `FileNotFoundError`), the code now logs a warning and skips processing for that specific path instead of crashing the node (CheckpointLoaderSimple was usually the first to break). This allows the rest of the directory traversal to proceed without interruption.
-
comfyanonymous authored
-
comfyanonymous authored
This is an alternative to VAE Encode for inpaint that should work with lower denoise. This is a different take on #2501
-
- 10 Jan, 2024 2 commits
-
-
comfyanonymous authored
-
comfyanonymous authored
-
- 09 Jan, 2024 2 commits
-
-
comfyanonymous authored
-
comfyanonymous authored
-
- 08 Jan, 2024 4 commits
-
-
comfyanonymous authored
-
comfyanonymous authored
-
pythongosssss authored
* wip per user data * Rename, hide menu * better error rework default user * store pretty * Add userdata endpoints Change nodetemplates to userdata * add multi user message * make normal arg * Fix tests * Ignore user dir * user tests * Changed to default to browser storage and add server-storage arg * fix crash on empty templates * fix settings added before load * ignore parse errors
-
comfyanonymous authored
-
- 07 Jan, 2024 2 commits
-
-
comfyanonymous authored
support masked attention.
-
comfyanonymous authored
-
- 06 Jan, 2024 3 commits
-
-
comfyanonymous authored
-
comfyanonymous authored
-
ramyma authored
-
- 05 Jan, 2024 2 commits
-
-
comfyanonymous authored
-
comfyanonymous authored
This node lets you generate a batch of images with different elevations or azimuths by setting the elevation_batch_increment and/or azimuth_batch_increment. It also sets the batch index for the latents so that the same init noise is used on each frame.
-
- 04 Jan, 2024 1 commit
-
-
comfyanonymous authored
A POST request to /free with: {"unload_models":true} will unload models from vram. A POST request to /free with: {"free_memory":true} will unload models and free all cached data from the last run workflow.
-
- 03 Jan, 2024 3 commits
-
-
comfyanonymous authored
-
comfyanonymous authored
-
comfyanonymous authored
This is an old model. Load the checkpoint like a regular one and use the new SD_4XUpscale_Conditioning node.
-
- 02 Jan, 2024 5 commits
-
-
comfyanonymous authored
-
comfyanonymous authored
Replace constants with downscale_ratio and latent_channels.
-
comfyanonymous authored
-
comfyanonymous authored
-
comfyanonymous authored
-
- 01 Jan, 2024 1 commit
-
-
comfyanonymous authored
-
- 31 Dec, 2023 2 commits
-
-
comfyanonymous authored
-
comfyanonymous authored
-
- 30 Dec, 2023 1 commit
-
-
comfyanonymous authored
-
- 29 Dec, 2023 4 commits
-
-
comfyanonymous authored
-
comfyanonymous authored
Allow VALIDATE_INPUTS to only validate specific inputs.
-
comfyanonymous authored
-
comfyanonymous authored
-
- 28 Dec, 2023 1 commit
-
-
comfyanonymous authored
-
- 27 Dec, 2023 3 commits
-
-
comfyanonymous authored
-
comfyanonymous authored
-
AYF authored
* Add `title` to the API workflow json. * API: Move `title` to `_meta` dictionary, imply unused.
-
- 26 Dec, 2023 1 commit
-
-
comfyanonymous authored
-