qnloft
/
ComfyUI
mirror of https://github.com/comfyanonymous/ComfyUI.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
2,685 Commits 6 Branches 27 Tags 118 MiB
Commit Graph

2685 Commits

Author SHA1 Message Date
comfyanonymous c6951548cf Update optimized_attention_for_device function for new functions that 
support masked attention.
 2024-01-07 13:52:08 -05:00
comfyanonymous aaa9017302 Add attention mask support to sub quad attention. 2024-01-07 04:13:58 -05:00
comfyanonymous 0c2c9fbdfa Support attention mask in split attention. 2024-01-06 13:16:48 -05:00
comfyanonymous 3ad0191bfb Implement attention mask on xformers. 2024-01-06 04:33:03 -05:00
ramyma af94eb14e3 fix: `/free` handler function name 2024-01-06 04:27:09 +02:00
comfyanonymous 7c9a0f7e0a Fix BasicScheduler issue with Loras. 2024-01-05 12:31:13 -05:00
comfyanonymous 35322a3766 StableZero123_Conditioning_Batched node. 
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.
 2024-01-05 04:20:03 -05:00
comfyanonymous 6d281b4ff4 Add a /free route to unload models or free all memory. 
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.
 2024-01-04 17:15:22 -05:00
comfyanonymous 8c6493578b Implement noise augmentation for SD 4X upscale model. 2024-01-03 14:27:11 -05:00
comfyanonymous ef4f6037cb Fix model patches not working in custom sampling scheduler nodes. 2024-01-03 12:16:30 -05:00
comfyanonymous a7874d1a8b Add support for the stable diffusion x4 upscaling model. 
This is an old model.

Load the checkpoint like a regular one and use the new
SD_4XUpscale_Conditioning node.
 2024-01-03 03:37:56 -05:00
comfyanonymous 2c4e92a98b Fix regression. 2024-01-02 14:41:33 -05:00
comfyanonymous 5eddfdd80c Refactor VAE code. 
Replace constants with downscale_ratio and latent_channels.
 2024-01-02 13:24:34 -05:00
comfyanonymous 8e2c99e3cf Fix issue when websocket is deleted when data is being sent. 2024-01-02 11:50:00 -05:00
comfyanonymous a47f609f90 Auto detect out_channels from model. 2024-01-02 01:50:57 -05:00
comfyanonymous 79f73a4b33 Remove useless code. 2024-01-02 01:50:29 -05:00
comfyanonymous 66831eb6e9 Add node id and prompt id to websocket progress packet. 2024-01-01 14:27:56 -05:00
comfyanonymous d1f3637a5a Add a denoise parameter to BasicScheduler node. 2023-12-31 15:37:20 -05:00
comfyanonymous 36e15f2507 Reregister nodes when pressing refresh button. 2023-12-31 05:05:14 -05:00
comfyanonymous 1b103e0cb2 Add argument to run the VAE on the CPU. 2023-12-30 05:49:07 -05:00
comfyanonymous 144e6580a4 This cache timeout is pretty useless in practice. 2023-12-29 17:47:24 -05:00
comfyanonymous 04b713dda1 Fix VALIDATE_INPUTS getting called multiple times. 
Allow VALIDATE_INPUTS to only validate specific inputs.
 2023-12-29 17:36:40 -05:00
comfyanonymous 12e822c6c8 Use function to calculate model size in model patcher. 2023-12-28 21:46:20 -05:00
comfyanonymous e1e322cf69 Load weights that can't be lowvramed to target device. 2023-12-28 21:41:10 -05:00
comfyanonymous a8baa40d85 Cleanup. 2023-12-28 12:23:07 -05:00
comfyanonymous c782144433 Fix clip vision lowvram mode not working. 2023-12-27 13:50:57 -05:00
comfyanonymous e478b1794e Only add _meta title to api prompt when dev mode is enabled in UI. 2023-12-27 01:07:02 -05:00
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.
 2023-12-27 00:55:11 -05:00
comfyanonymous f21bb41787 Fix taesd VAE in lowvram mode. 2023-12-26 12:52:21 -05:00
comfyanonymous 61b3f15f8f Fix lowvram mode not working with unCLIP and Revision code. 2023-12-26 05:02:02 -05:00
shiimizu 392878a262 Fix hiding dom widgets. 2023-12-25 19:17:40 -08:00
comfyanonymous 257c2eaaa4 Merge branch 'patch-1' of https://github.com/savolla/ComfyUI 2023-12-25 12:24:31 -05:00
comfyanonymous d0165d819a Fix SVD lowvram mode. 2023-12-24 07:13:18 -05:00
comfyanonymous a252963f95 --disable-smart-memory now unloads everything like it did originally. 2023-12-23 04:25:06 -05:00
comfyanonymous 36a7953142 Greatly improve lowvram sampling speed by getting rid of accelerate. 
Let me know if this breaks anything.
 2023-12-22 14:38:45 -05:00
comfyanonymous 261bcbb0d9 A few missing comfy ops in the VAE. 2023-12-22 04:05:42 -05:00
comfyanonymous d35267e85a Litegraph updates. 
Update from upstream repo.

Auto select value in prompt.

Increase maximum number of nodes to 10k.
 2023-12-21 13:21:25 -05:00
comfyanonymous 6781b181ef Fix potential tensor device issue with ImageCompositeMasked. 2023-12-21 02:35:01 -05:00
comfyanonymous a1e1c69f7d LoadImage now loads all the frames from animated images as a batch. 2023-12-20 16:39:09 -05:00
comfyanonymous 5f54614e7f Add a RebatchImages node. 2023-12-20 16:22:18 -05:00
comfyanonymous e82942cc29 Add a denoise parameter to the SDTurboScheduler. 2023-12-20 02:54:25 -05:00
comfyanonymous ba3f3aa1ca Merge branch 'test-reliability' of https://github.com/pythongosssss/ComfyUI 2023-12-19 16:32:53 -05:00
pythongosssss 8680ac3dfd try to improve test reliability 2023-12-19 20:38:07 +00:00
pythongosssss e65110fd93 Fix dom widgets not being hidden 2023-12-19 20:22:01 +00:00
Oleksiy Nehlyadyuk 40ea2bd011
Update requirements.txt 
the UI launches with one missing module `torchvision`. spits out a `ModuleNotFoundError`. installing `torchvision` module fixed it.
 2023-12-19 17:07:55 +03:00
comfyanonymous 9a7619b72d Fix regression with inpaint model. 2023-12-19 02:32:59 -05:00
comfyanonymous 571ea8cdcc Fix SAG not working with cfg 1.0 2023-12-18 17:03:32 -05:00
comfyanonymous 8cf1daa108 Fix SDXL area composition sometimes not using the right pooled output. 2023-12-18 12:54:23 -05:00
comfyanonymous d2f322902c Fix wrong Stable Zero123 node name. 2023-12-18 03:59:50 -05:00
comfyanonymous 2258f85159 Support stable zero 123 model. 
To use it use the ImageOnlyCheckpointLoader to load the checkpoint and
the new Stable_Zero123 node.
 2023-12-18 03:48:04 -05:00