Commit Graph

  • 0d45efb7d6 Fixed Issue with LoadImage node when loading PNG files with embedded ICC profiles. (#3316) shawnington 2024-05-04 02:32:41 -05:00
  • daa92a8ff4 Fix potential issues with the int rounding fix. comfyanonymous 2024-05-03 05:49:21 -04:00
  • 89d0e9abeb Fix int widgets rounding. comfyanonymous 2024-05-02 03:34:19 -04:00
  • a56d02efc7 Change torch.xpu to ipex.optimize, xpu device initialization and remove workaround for text node issue from older IPEX. (#3388) Simon Lui 2024-05-02 00:26:50 -07:00
  • f81a6fade8 Fix some edge cases with samplers and arrays with a single sigma. comfyanonymous 2024-05-01 17:05:30 -04:00
  • 94d5a12801 Don't load the model in SDTurboScheduler comfyanonymous 2024-05-01 16:57:10 -04:00
  • 2aed53c4ac Workaround xformers bug. comfyanonymous 2024-04-30 21:23:40 -04:00
  • bacce529fb Add TLS Support (#3312) Garrett Sutula 2024-04-30 20:17:02 -04:00
  • bb8b48a260 Update Readme. comfyanonymous 2024-04-30 20:11:34 -04:00
  • eecd69b53a Add a SamplerLCMUpscale node. comfyanonymous 2024-04-29 20:00:47 -04:00
  • 059773a6df Add some nodes to multiply the attention in UNet and Clip models. comfyanonymous 2024-04-28 12:50:22 -04:00
  • 10fcd09f4a Add a denoise value to AlignYourStepsScheduler. comfyanonymous 2024-04-27 00:14:06 -04:00
  • 8cab3be673 Update command for AMD stable pytorch install in README. comfyanonymous 2024-04-26 15:44:12 -04:00
  • 7990ae18c1 Fix error when more cond masks passed in than batch size (#3353) Jedrzej Kosinski 2024-04-26 11:51:12 -05:00
  • 16eabdf70d Free more vram for upscale models. comfyanonymous 2024-04-25 17:04:19 -04:00
  • 8dc19e40d1 Don't init a VAE model when there are no VAE weights. comfyanonymous 2024-04-24 09:20:31 -04:00
  • 27d5808fc4 Increase max lora strength to 100.0 comfyanonymous 2024-04-23 13:07:39 -04:00
  • b8218522f1 Increase sigma_min/sigma_max range for custom schedulers (#3317) Pam 2024-04-23 18:40:10 +05:00
  • d09b5ef4ef Free some memory before loading upscale models. comfyanonymous 2024-04-22 18:42:41 -04:00
  • 4ee9aad6ca Speed up Sharpen node. comfyanonymous 2024-04-21 09:02:06 -04:00
  • 644a3ae58d Implement Align Your Steps as a AlignYourStepsScheduler node. comfyanonymous 2024-04-20 04:31:49 -04:00
  • 133dc3351b Faster blur. comfyanonymous 2024-04-19 03:52:02 -04:00
  • 5d08802f78 Sync some minor changes from the other repo. comfyanonymous 2024-04-19 03:43:09 -04:00
  • c59fe9f254 Support VAE without quant_conv. comfyanonymous 2024-04-18 21:05:33 -04:00
  • a88b0ebc2d Improve node input/widget conversion sub-menus (#3281) Torbjörn Lönnemark 2024-04-18 22:41:23 +02:00
  • d64e217427 Fix annoying float issue causing the value to be rounded to above the max. comfyanonymous 2024-04-17 17:34:02 -04:00
  • 072e3bd2b5 Fixed an issue where the main menu disappears intermittently as the coordinates become negative. (#3269) Dr.Lt.Data 2024-04-18 05:36:49 +09:00
  • abc69cab45 Add a helpful warning for links that don't point anywhere. comfyanonymous 2024-04-17 12:28:05 -04:00
  • 45ec1cbe96 Implement PerpNeg as a guider. comfyanonymous 2024-04-16 02:57:01 -04:00
  • 8903dce862 This can be removed since PAG doesn't use the uncond. comfyanonymous 2024-04-15 12:14:00 -04:00
  • 719fb2c81d Add basic PAG node. comfyanonymous 2024-04-14 23:34:25 -04:00
  • 258dbc06c3 Fix some memory related issues. comfyanonymous 2024-04-14 12:08:58 -04:00
  • 744ac944db Don't make dynamicPrompts the default on multiline string inputs. comfyanonymous 2024-04-13 16:12:09 -04:00
  • 58812ab8ca Support SDXS 512 model. comfyanonymous 2024-04-12 22:12:35 -04:00
  • 0256e7f769 Fix tests. comfyanonymous 2024-04-12 20:01:34 -04:00
  • 2bef134ebf change Convert.. input (#3246) NyaamZ 2024-04-13 06:02:17 +09:00
  • 4bd7d55b90 Add some colors to SamplerCustom links. comfyanonymous 2024-04-11 22:43:05 -04:00
  • fd7c636680 Add an AddNoise node to add noise depending on the sigma. comfyanonymous 2024-04-10 20:29:35 -04:00
  • 831511a1ee Fix issue with sampling_settings persisting across models. comfyanonymous 2024-04-09 23:20:43 -04:00
  • 4201181b35 Add ModelMergeSD1, ModelMergeSD2 and ModelMergeSDXL. comfyanonymous 2024-04-09 04:25:45 -04:00
  • 30abc324c2 Support properly saving CosXL checkpoints. comfyanonymous 2024-04-08 00:36:22 -04:00
  • d644b6bcd8 Cleanup some more conditioning nodes. comfyanonymous 2024-04-07 14:40:43 -04:00
  • c9fc242e2c The middle prompt should be treated more as a negative prompt. comfyanonymous 2024-04-07 14:34:43 -04:00
  • 80bda6c163 Cleanup a few conditioning nodes. comfyanonymous 2024-04-07 14:27:40 -04:00
  • 0a03009808 Fix issue with controlnet models getting loaded multiple times. comfyanonymous 2024-04-06 18:38:39 -04:00
  • de172f8be7 Improve A1111 metadata parsing (#3216) Gorka Eguileor 2024-04-06 18:10:17 +02:00
  • d8dea4cdb8 Fix DisableNoise node. comfyanonymous 2024-04-05 21:36:23 -04:00
  • a7dd82e668 Fix copy paste issue with litegraph. comfyanonymous 2024-04-05 14:59:05 -04:00
  • 38ed2da2dd Fix typo in lowvram patcher (#3209) kk-89 2024-04-05 09:02:13 -07:00
  • ea9ac9d30b Fix PerpNeg node. comfyanonymous 2024-04-05 11:33:36 -04:00
  • 1088d1850f Support for CosXL models. comfyanonymous 2024-04-05 10:40:27 -04:00
  • 41ed7e85ea Fix object_patches_backup not being the same object across clones. comfyanonymous 2024-04-05 00:22:44 -04:00
  • 0f5768e038 Fix missing arguments in cfg_function. comfyanonymous 2024-04-04 23:38:57 -04:00
  • 1f4fc9ea0c Fix issue with get_model_object on patched model. comfyanonymous 2024-04-04 23:01:02 -04:00
  • 1a0486bb96 Fix model needing to be loaded on GPU to generate the sigmas. comfyanonymous 2024-04-04 22:08:49 -04:00
  • 1f8d8e6c77 Add InstructPixToPixConditioning node. comfyanonymous 2024-04-04 15:06:17 -04:00
  • 5272fd4b03 Add DualCFGGuider used in IP2P models for example. comfyanonymous 2024-04-04 14:57:44 -04:00
  • cfbf3be54b Add basic guider for models with no cfg. comfyanonymous 2024-04-04 13:57:32 -04:00
  • c6bd456c45 Make zero denoise a NOP. comfyanonymous 2024-04-04 11:38:25 -04:00
  • fcfd2bdf8a Small cleanup. comfyanonymous 2024-04-04 11:16:49 -04:00
  • f117566299 SamplerCustomAdvanced node. comfyanonymous 2024-04-04 01:32:25 -04:00
  • 0542088ef8 Refactor sampler code for more advanced sampler nodes part 2. comfyanonymous 2024-04-04 00:48:42 -04:00
  • 57753c964a Refactor sampling code for more advanced sampler nodes. comfyanonymous 2024-04-03 16:34:19 -04:00
  • 6c6a39251f Fix saving text encoder in fp8. comfyanonymous 2024-04-02 11:46:34 -04:00
  • e6482fbbfc Refactor calc_cond_uncond_batch into calc_cond_batch. comfyanonymous 2024-04-01 17:23:07 -04:00
  • 1306464538 --force-fp16 is no longer necessary on Mac. comfyanonymous 2024-03-31 12:50:28 -04:00
  • 575acb69e4 IP2P model loading support. comfyanonymous 2024-03-31 01:25:16 -04:00
  • 96b4c757cf Add log to debug custom nodes that hang when imported. comfyanonymous 2024-03-30 11:52:11 -04:00
  • 94a5a67c32 Cleanup to support different types of inpaint models. comfyanonymous 2024-03-29 14:43:24 -04:00
  • 9bf6061dfc Switch prints to logging in folder_paths and add some extra debug. comfyanonymous 2024-03-29 03:07:13 -04:00
  • 5d8898c056 Fix some performance issues with weight loading and unloading. comfyanonymous 2024-03-28 18:01:04 -04:00
  • 327ca1313d Support SDXS 0.9 comfyanonymous 2024-03-27 23:51:17 -04:00
  • 8ae1e4d125 Make step on sharpen node smaller. comfyanonymous 2024-03-27 01:28:31 -04:00
  • 2f93b91646 Add Tesla GPUs to cuda malloc blacklist. comfyanonymous 2024-03-26 19:33:40 -04:00
  • c9673926fb Fix test. comfyanonymous 2024-03-26 04:07:30 -04:00
  • 11838e60f4 Increase the max resolution. comfyanonymous 2024-03-26 04:00:53 -04:00
  • ae77590b4e dora_scale support for lora file. comfyanonymous 2024-03-25 18:09:23 -04:00
  • c6de09b02e Optimize memory unload strategy for more optimized performance. comfyanonymous 2024-03-24 02:36:30 -04:00
  • 6a32c06f06 Move cleanup_models to improve performance. comfyanonymous 2024-03-23 17:27:10 -04:00
  • a28a9dc836 Add an example to use the SaveImageWebsocket node and enable it. comfyanonymous 2024-03-22 12:56:48 -04:00
  • 0624838237 Add inverse noise scaling function. comfyanonymous 2024-03-21 14:49:11 -04:00
  • 5d875d77fe Fix regression with lcm not working with batches. comfyanonymous 2024-03-20 20:48:54 -04:00
  • 4b9005e949 Fix regression with model merging. comfyanonymous 2024-03-20 13:53:45 -04:00
  • c18a203a8a Don't unload model weights for non weight patches. comfyanonymous 2024-03-20 01:29:26 -04:00
  • 150a3e946f Make LCM sampler use the model noise scaling function. comfyanonymous 2024-03-20 01:35:59 -04:00
  • d14bdb1896 Revert, NOTE: this will be removed again soon please fix your nodes. comfyanonymous 2024-03-19 11:17:37 -04:00
  • 0c55f16c9e Remove code that should be useless now. comfyanonymous 2024-03-19 02:34:01 -04:00
  • 40e124c6be SV3D support. comfyanonymous 2024-03-18 10:04:51 -04:00
  • 0b78213bda Fix neg scale step. comfyanonymous 2024-03-18 15:51:23 -04:00
  • b1a16d4500 Fix stable cascade img2img not working with all resolutions. comfyanonymous 2024-03-18 13:50:11 -04:00
  • cacb022c4a Make saved SD1 checkpoints match more closely the official one. comfyanonymous 2024-03-18 00:26:23 -04:00
  • d3406d8d58 Increase image batch nodes maximum values. comfyanonymous 2024-03-17 08:57:49 -04:00
  • d7897fff2c Move cascade scale factor from stage_a to latent_formats.py comfyanonymous 2024-03-16 14:49:35 -04:00
  • f2fe635c9f SamplerDPMAdaptative node to test the different options. comfyanonymous 2024-03-15 19:34:22 -04:00
  • 448d9263a2 Fix control loras breaking. comfyanonymous 2024-03-14 09:30:21 -04:00
  • db8b59ecff Lower memory usage for loras in lowvram mode at the cost of perf. comfyanonymous 2024-03-13 19:04:41 -04:00
  • eda8704386 Add SamplerDPMPP_3M_SDE node. comfyanonymous 2024-03-12 12:16:37 -04:00
  • e7b8e240f7 Add SamplerLMS node. comfyanonymous 2024-03-12 04:34:34 -04:00
  • 2a813c3b09 Switch some more prints to logging. comfyanonymous 2024-03-11 16:24:47 -04:00
  • 0ed72befe1 Change log levels. comfyanonymous 2024-03-11 13:54:56 -04:00