comfyanonymous
|
5eddfdd80c
|
Refactor VAE code.
Replace constants with downscale_ratio and latent_channels.
|
11 months ago |
|
comfyanonymous
|
8e2c99e3cf
|
Fix issue when websocket is deleted when data is being sent.
|
11 months ago |
|
comfyanonymous
|
a47f609f90
|
Auto detect out_channels from model.
|
11 months ago |
|
comfyanonymous
|
79f73a4b33
|
Remove useless code.
|
11 months ago |
|
comfyanonymous
|
66831eb6e9
|
Add node id and prompt id to websocket progress packet.
|
11 months ago |
|
comfyanonymous
|
d1f3637a5a
|
Add a denoise parameter to BasicScheduler node.
|
11 months ago |
|
comfyanonymous
|
36e15f2507
|
Reregister nodes when pressing refresh button.
|
11 months ago |
|
comfyanonymous
|
1b103e0cb2
|
Add argument to run the VAE on the CPU.
|
11 months ago |
|
comfyanonymous
|
144e6580a4
|
This cache timeout is pretty useless in practice.
|
11 months ago |
|
comfyanonymous
|
04b713dda1
|
Fix VALIDATE_INPUTS getting called multiple times.
Allow VALIDATE_INPUTS to only validate specific inputs.
|
11 months ago |
|
comfyanonymous
|
12e822c6c8
|
Use function to calculate model size in model patcher.
|
11 months ago |
|
comfyanonymous
|
e1e322cf69
|
Load weights that can't be lowvramed to target device.
|
11 months ago |
|
comfyanonymous
|
a8baa40d85
|
Cleanup.
|
11 months ago |
|
comfyanonymous
|
c782144433
|
Fix clip vision lowvram mode not working.
|
11 months ago |
|
comfyanonymous
|
e478b1794e
|
Only add _meta title to api prompt when dev mode is enabled in UI.
|
11 months ago |
AYF
|
f15dce71fd
|
Add title to the API workflow json. (#2380)
* Add `title` to the API workflow json.
* API: Move `title` to `_meta` dictionary, imply unused.
|
11 months ago |
|
comfyanonymous
|
f21bb41787
|
Fix taesd VAE in lowvram mode.
|
11 months ago |
|
comfyanonymous
|
61b3f15f8f
|
Fix lowvram mode not working with unCLIP and Revision code.
|
11 months ago |
shiimizu
|
392878a262
|
Fix hiding dom widgets.
|
11 months ago |
|
comfyanonymous
|
257c2eaaa4
|
Merge branch 'patch-1' of https://github.com/savolla/ComfyUI
|
11 months ago |
|
comfyanonymous
|
d0165d819a
|
Fix SVD lowvram mode.
|
11 months ago |
|
comfyanonymous
|
a252963f95
|
--disable-smart-memory now unloads everything like it did originally.
|
11 months ago |
|
comfyanonymous
|
36a7953142
|
Greatly improve lowvram sampling speed by getting rid of accelerate.
Let me know if this breaks anything.
|
11 months ago |
|
comfyanonymous
|
261bcbb0d9
|
A few missing comfy ops in the VAE.
|
11 months ago |
|
comfyanonymous
|
d35267e85a
|
Litegraph updates.
Update from upstream repo.
Auto select value in prompt.
Increase maximum number of nodes to 10k.
|
11 months ago |
|
comfyanonymous
|
6781b181ef
|
Fix potential tensor device issue with ImageCompositeMasked.
|
11 months ago |
|
comfyanonymous
|
a1e1c69f7d
|
LoadImage now loads all the frames from animated images as a batch.
|
11 months ago |
|
comfyanonymous
|
5f54614e7f
|
Add a RebatchImages node.
|
11 months ago |
|
comfyanonymous
|
e82942cc29
|
Add a denoise parameter to the SDTurboScheduler.
|
11 months ago |
|
comfyanonymous
|
ba3f3aa1ca
|
Merge branch 'test-reliability' of https://github.com/pythongosssss/ComfyUI
|
11 months ago |
pythongosssss
|
8680ac3dfd
|
try to improve test reliability
|
11 months ago |
|
pythongosssss
|
e65110fd93
|
Fix dom widgets not being hidden
|
11 months ago |
Oleksiy Nehlyadyuk
|
40ea2bd011
|
Update requirements.txt
the UI launches with one missing module `torchvision`. spits out a `ModuleNotFoundError`. installing `torchvision` module fixed it.
|
11 months ago |
|
comfyanonymous
|
9a7619b72d
|
Fix regression with inpaint model.
|
11 months ago |
|
comfyanonymous
|
571ea8cdcc
|
Fix SAG not working with cfg 1.0
|
11 months ago |
|
comfyanonymous
|
8cf1daa108
|
Fix SDXL area composition sometimes not using the right pooled output.
|
11 months ago |
|
comfyanonymous
|
d2f322902c
|
Fix wrong Stable Zero123 node name.
|
11 months ago |
|
comfyanonymous
|
2258f85159
|
Support stable zero 123 model.
To use it use the ImageOnlyCheckpointLoader to load the checkpoint and
the new Stable_Zero123 node.
|
11 months ago |
|
comfyanonymous
|
2f9d6a97ec
|
Add --deterministic option to make pytorch use deterministic algorithms.
|
11 months ago |
|
comfyanonymous
|
a036b94075
|
Move SaveAnimated nodes to image->animation.
|
11 months ago |
|
pythongosssss
|
6453dc1ca2
|
Fix name counter preventing more than 3 of the same node
Fix linked widget offset when populating values
|
11 months ago |
|
comfyanonymous
|
e45d920ae3
|
Don't resize clip vision image when the size is already good.
|
11 months ago |
|
comfyanonymous
|
13e6d5366e
|
Switch clip vision to manual cast.
Make it use the same dtype as the text encoder.
|
11 months ago |
|
comfyanonymous
|
574efd3782
|
Fix perpneg not working on SDXL.
|
11 months ago |
|
comfyanonymous
|
172984db01
|
Fix SAG not working on certain resolutions.
|
11 months ago |
|
comfyanonymous
|
6596654d47
|
Add a LatentBatch node.
|
11 months ago |
|
comfyanonymous
|
719fa0866f
|
Set clip vision model in eval mode so it works without inference mode.
|
11 months ago |
|
comfyanonymous
|
adc40e3d7b
|
Forgot this.
|
11 months ago |
|
comfyanonymous
|
014c8bf2f2
|
Refactor LCM to support more model types.
|
11 months ago |
|
comfyanonymous
|
9cad2f06ff
|
Make perp neg take a conditioning input instead of a CLIP one.
|
11 months ago |
