andreas/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Commit Graph

  • 6a7bc35db8 Use basic attention implementation for small inputs on old pytorch. comfyanonymous 2024-01-09 13:46:52 -05:00
  • b3b5ddb07a Support I mode images in LoadImageMask. comfyanonymous 2024-01-08 17:08:17 -05:00
  • 2d74fc4360 Fix issue with user manager parent dir not being created. comfyanonymous 2024-01-08 17:08:00 -05:00
  • 235727fed7 Store user settings/data on the server and multi user support (#2160) pythongosssss 2024-01-08 22:06:44 +00:00
  • 6a10640f0d Support properly loading images with mode I. comfyanonymous 2024-01-08 03:46:36 -05:00
  • c6951548cf Update optimized_attention_for_device function for new functions that support masked attention. comfyanonymous 2024-01-07 13:52:08 -05:00
  • aaa9017302 Add attention mask support to sub quad attention. comfyanonymous 2024-01-07 04:13:58 -05:00
  • 0c2c9fbdfa Support attention mask in split attention. comfyanonymous 2024-01-06 13:16:48 -05:00
  • 3ad0191bfb Implement attention mask on xformers. comfyanonymous 2024-01-06 04:33:03 -05:00
  • af94eb14e3 fix: /free handler function name ramyma 2024-01-06 04:27:09 +02:00
  • 7c9a0f7e0a Fix BasicScheduler issue with Loras. comfyanonymous 2024-01-05 12:31:13 -05:00
  • 35322a3766 StableZero123_Conditioning_Batched node. comfyanonymous 2024-01-05 04:20:03 -05:00
  • 6d281b4ff4 Add a /free route to unload models or free all memory. comfyanonymous 2024-01-04 14:28:11 -05:00
  • 8c6493578b Implement noise augmentation for SD 4X upscale model. comfyanonymous 2024-01-03 14:27:11 -05:00
  • ef4f6037cb Fix model patches not working in custom sampling scheduler nodes. comfyanonymous 2024-01-03 12:16:30 -05:00
  • a7874d1a8b Add support for the stable diffusion x4 upscaling model. comfyanonymous 2024-01-03 03:30:39 -05:00
  • 2c4e92a98b Fix regression. comfyanonymous 2024-01-02 14:41:33 -05:00
  • 5eddfdd80c Refactor VAE code. comfyanonymous 2024-01-02 13:24:34 -05:00
  • 8e2c99e3cf Fix issue when websocket is deleted when data is being sent. comfyanonymous 2024-01-02 11:50:00 -05:00
  • a47f609f90 Auto detect out_channels from model. comfyanonymous 2024-01-02 01:50:57 -05:00
  • 79f73a4b33 Remove useless code. comfyanonymous 2024-01-02 01:50:29 -05:00
  • 66831eb6e9 Add node id and prompt id to websocket progress packet. comfyanonymous 2024-01-01 14:27:56 -05:00
  • d1f3637a5a Add a denoise parameter to BasicScheduler node. comfyanonymous 2023-12-31 15:37:20 -05:00
  • 36e15f2507 Reregister nodes when pressing refresh button. comfyanonymous 2023-12-31 05:05:14 -05:00
  • 1b103e0cb2 Add argument to run the VAE on the CPU. comfyanonymous 2023-12-30 05:38:21 -05:00
  • 144e6580a4 This cache timeout is pretty useless in practice. comfyanonymous 2023-12-29 17:47:24 -05:00
  • 04b713dda1 Fix VALIDATE_INPUTS getting called multiple times. comfyanonymous 2023-12-29 17:33:30 -05:00
  • 12e822c6c8 Use function to calculate model size in model patcher. comfyanonymous 2023-12-28 21:46:20 -05:00
  • e1e322cf69 Load weights that can't be lowvramed to target device. comfyanonymous 2023-12-28 21:41:10 -05:00
  • a8baa40d85 Cleanup. comfyanonymous 2023-12-28 12:23:07 -05:00
  • c782144433 Fix clip vision lowvram mode not working. comfyanonymous 2023-12-27 13:50:57 -05:00
  • e478b1794e Only add _meta title to api prompt when dev mode is enabled in UI. comfyanonymous 2023-12-27 01:07:02 -05:00
  • f15dce71fd Add title to the API workflow json. (#2380) AYF 2023-12-27 00:55:11 -05:00
  • f21bb41787 Fix taesd VAE in lowvram mode. comfyanonymous 2023-12-26 12:52:21 -05:00
  • 61b3f15f8f Fix lowvram mode not working with unCLIP and Revision code. comfyanonymous 2023-12-26 05:02:02 -05:00
  • 392878a262 Fix hiding dom widgets. shiimizu 2023-12-25 19:17:40 -08:00
  • 257c2eaaa4 Merge branch 'patch-1' of https://github.com/savolla/ComfyUI comfyanonymous 2023-12-25 12:24:31 -05:00
  • d0165d819a Fix SVD lowvram mode. comfyanonymous 2023-12-24 07:06:59 -05:00
  • a252963f95 --disable-smart-memory now unloads everything like it did originally. comfyanonymous 2023-12-23 04:25:06 -05:00
  • 36a7953142 Greatly improve lowvram sampling speed by getting rid of accelerate. comfyanonymous 2023-12-22 14:24:04 -05:00
  • 261bcbb0d9 A few missing comfy ops in the VAE. comfyanonymous 2023-12-22 04:05:42 -05:00
  • d35267e85a Litegraph updates. comfyanonymous 2023-12-21 13:21:25 -05:00
  • 6781b181ef Fix potential tensor device issue with ImageCompositeMasked. comfyanonymous 2023-12-21 02:35:01 -05:00
  • a1e1c69f7d LoadImage now loads all the frames from animated images as a batch. comfyanonymous 2023-12-20 16:39:09 -05:00
  • 5f54614e7f Add a RebatchImages node. comfyanonymous 2023-12-20 16:22:18 -05:00
  • e82942cc29 Add a denoise parameter to the SDTurboScheduler. comfyanonymous 2023-12-20 02:51:18 -05:00
  • ba3f3aa1ca Merge branch 'test-reliability' of https://github.com/pythongosssss/ComfyUI comfyanonymous 2023-12-19 16:32:53 -05:00
  • 8680ac3dfd try to improve test reliability pythongosssss 2023-12-19 20:38:07 +00:00
  • e65110fd93 Fix dom widgets not being hidden pythongosssss 2023-12-19 20:22:01 +00:00
  • 40ea2bd011 Update requirements.txt Oleksiy Nehlyadyuk 2023-12-19 17:07:55 +03:00
  • 9a7619b72d Fix regression with inpaint model. comfyanonymous 2023-12-19 02:32:59 -05:00
  • 571ea8cdcc Fix SAG not working with cfg 1.0 comfyanonymous 2023-12-18 17:03:32 -05:00
  • 8cf1daa108 Fix SDXL area composition sometimes not using the right pooled output. comfyanonymous 2023-12-18 12:54:23 -05:00
  • d2f322902c Fix wrong Stable Zero123 node name. comfyanonymous 2023-12-18 03:59:50 -05:00
  • 2258f85159 Support stable zero 123 model. comfyanonymous 2023-12-18 03:18:40 -05:00
  • 2f9d6a97ec Add --deterministic option to make pytorch use deterministic algorithms. comfyanonymous 2023-12-17 16:59:21 -05:00
  • a036b94075 Move SaveAnimated nodes to image->animation. comfyanonymous 2023-12-17 02:37:22 -05:00
  • 6453dc1ca2 Fix name counter preventing more than 3 of the same node Fix linked widget offset when populating values pythongosssss 2023-12-16 14:16:12 +00:00
  • e45d920ae3 Don't resize clip vision image when the size is already good. comfyanonymous 2023-12-16 03:06:10 -05:00
  • 13e6d5366e Switch clip vision to manual cast. comfyanonymous 2023-12-16 02:47:26 -05:00
  • 574efd3782 Fix perpneg not working on SDXL. comfyanonymous 2023-12-16 02:30:16 -05:00
  • 172984db01 Fix SAG not working on certain resolutions. comfyanonymous 2023-12-16 01:29:57 -05:00
  • 6596654d47 Add a LatentBatch node. comfyanonymous 2023-12-16 01:21:00 -05:00
  • 719fa0866f Set clip vision model in eval mode so it works without inference mode. comfyanonymous 2023-12-15 18:53:08 -05:00
  • adc40e3d7b Forgot this. comfyanonymous 2023-12-15 15:46:23 -05:00
  • 014c8bf2f2 Refactor LCM to support more model types. comfyanonymous 2023-12-15 15:26:12 -05:00
  • 9cad2f06ff Make perp neg take a conditioning input instead of a CLIP one. comfyanonymous 2023-12-15 14:40:57 -05:00
  • 574363a8a6 Implement Perp-Neg Hari 2023-12-16 00:28:16 +05:30
  • a5056cfb1f Remove useless code. comfyanonymous 2023-12-15 01:28:16 -05:00
  • b12b48e170 cleanup. comfyanonymous 2023-12-14 20:11:46 -05:00
  • 329c571993 Improve code legibility. comfyanonymous 2023-12-14 11:41:49 -05:00
  • 6c5990f7db Fix cfg being calculated more than once if sampler_cfg_function. comfyanonymous 2023-12-13 20:28:04 -05:00
  • ba04a87d10 Refactor and improve the sag node. comfyanonymous 2023-12-13 16:10:03 -05:00
  • 6761233e9d Implement Self-Attention Guidance (#2201) Rafie Walker 2023-12-13 21:52:11 +01:00
  • 390078904c Group node fixes (#2259) pythongosssss 2023-12-13 05:56:39 +00:00
  • b454a67bb9 Support segmind vega model. comfyanonymous 2023-12-12 19:09:53 -05:00
  • 824e4935f5 Add dtype parameter to VAE object. comfyanonymous 2023-12-12 12:03:29 -05:00
  • 32b7e7e769 Add manual cast to controlnet. comfyanonymous 2023-12-12 03:32:23 -05:00
  • 3152023fbc Use inference dtype for unet memory usage estimation. comfyanonymous 2023-12-11 23:50:38 -05:00
  • 77755ab8db Refactor comfy.ops comfyanonymous 2023-12-11 23:27:13 -05:00
  • b0aab1e4ea Add an option --fp16-unet to force using fp16 for the unet. comfyanonymous 2023-12-11 18:36:29 -05:00
  • ba07cb748e Use faster manual cast for fp8 in unet. comfyanonymous 2023-12-11 18:24:44 -05:00
  • ab93abd4b2 Prevent cleaning graph state on undo/redo (#2255) pythongosssss 2023-12-11 17:33:35 +00:00
  • 57926635e8 Switch text encoder to manual cast. comfyanonymous 2023-12-10 23:00:54 -05:00
  • 69033081c5 mask editor bugfix - Addressing the issue where an unnecessary hidden panel disrupts the drawing. Dr.Lt.Data 2023-12-11 00:24:16 +09:00
  • 340177e6e8 Disable non blocking on mps. comfyanonymous 2023-12-10 01:30:35 -05:00
  • 614b7e731f Implement GLora. comfyanonymous 2023-12-09 18:15:26 -05:00
  • cb63e230b4 Make lora code a bit cleaner. comfyanonymous 2023-12-09 14:15:09 -05:00
  • 9e411073e9 Add instructions for those that have python 3.12 comfyanonymous 2023-12-09 13:41:30 -05:00
  • eccc9e64a6 Merge branch 'group-reroute-fix' of https://github.com/pythongosssss/ComfyUI comfyanonymous 2023-12-09 12:01:26 -05:00
  • da74e3bbe3 Update pytorch nightly packaging workflow. comfyanonymous 2023-12-09 12:01:17 -05:00
  • 174eba8e95 Use own clip vision model implementation. comfyanonymous 2023-12-09 11:56:31 -05:00
  • 080ef75c31 fix pythongosssss 2023-12-09 13:19:21 +00:00
  • 9aaf368a41 Fix internal reroutes connected to other groups pythongosssss 2023-12-09 13:04:35 +00:00
  • 97015b6b38 Cleanup. comfyanonymous 2023-12-08 16:02:08 -05:00
  • a4ec54a40d Add linear_start and linear_end to model_config.sampling_settings comfyanonymous 2023-12-08 02:49:30 -05:00
  • 9ac0b487ac Make --gpu-only put intermediate values in GPU memory instead of cpu. comfyanonymous 2023-12-08 02:35:45 -05:00
  • cdff081023 Fix hypertile. comfyanonymous 2023-12-07 15:22:35 -05:00
  • efb704c758 Support attention masking in CLIP implementation. comfyanonymous 2023-12-07 02:51:02 -05:00
  • 248d9125b0 Merge branch 'ht_deterministic' of https://github.com/asagi4/ComfyUI comfyanonymous 2023-12-07 01:45:11 -05:00