Commit Graph

1746 Commits

Author SHA1 Message Date
pythongosssss
49b97dc5d8 Apply value on connect 2023-11-04 12:35:31 +00:00
pythongosssss
4a31f461c8 Trigger callback on text change 2023-11-04 12:10:23 +00:00
pythongosssss
f9ff5d9105 Handle missing internal nodes 2023-11-04 11:44:01 +00:00
pythongosssss
b3f759d979 Fix links on convert to nodes 2023-11-04 11:30:33 +00:00
pythongosssss
b6fb105b95 Fix reconnecting output links on convert to group 2023-11-04 11:10:51 +00:00
comfyanonymous
1ffa8858e7 Move model sampling code to comfy/model_sampling.py 2023-11-04 01:32:23 -04:00
pythongosssss
4c928d2371 Merge remote-tracking branch 'origin/master' into group-nodes 2023-11-03 17:23:20 +00:00
comfyanonymous
ae2acfc21b Don't convert Nan to zero.
Converting Nan to zero is a bad idea because it makes it hard to tell when
something went wrong.
2023-11-03 13:13:15 -04:00
comfyanonymous
ee74ef5c9e Increase maximum batch size in LatentRebatch. 2023-11-02 13:07:41 -04:00
Matteo Spinelli
6e84a01ecc
Refactor the template manager (#1878)
* add drag-drop to node template manager

* better dnd, save field on change

* actually save templates

---------

Co-authored-by: matt3o <matt3o@gmail.com>
2023-11-02 12:29:57 -04:00
comfyanonymous
dd116abfc4 Merge branch 'quantize-dither' of https://github.com/tsone/ComfyUI 2023-11-02 00:57:00 -04:00
comfyanonymous
d2e27b48f1 sampler_cfg_function now gets the noisy output as argument again.
This should make things that use sampler_cfg_function behave like before.

Added an input argument for those that want the denoised output.

This means you can calculate the x0 prediction of the model by doing:
(input - cond) for example.
2023-11-01 21:24:08 -04:00
comfyanonymous
2455aaed8a Allow model or clip to be None in load_lora_for_models. 2023-11-01 20:27:20 -04:00
comfyanonymous
45a3df1cde Merge branch 'filter-widgets-crash-fix' of https://github.com/Jantolick/ComfyUI 2023-11-01 20:17:25 -04:00
comfyanonymous
ecb80abb58 Allow ModelSamplingDiscrete to be instantiated without a model config. 2023-11-01 19:13:03 -04:00
Joseph Antolick
88410ace9b fix: handle null case for currentNode widgets to prevent scroll error 2023-11-01 16:52:51 -04:00
comfyanonymous
e73ec8c4da Not used anymore. 2023-11-01 00:01:30 -04:00
comfyanonymous
111f1b5255 Fix some issues with sampling precision. 2023-10-31 23:49:29 -04:00
comfyanonymous
7c0f255de1 Clean up percent start/end and make controlnets work with sigmas. 2023-10-31 22:14:32 -04:00
comfyanonymous
a268a574fa Remove a bunch of useless code.
DDIM is the same as euler with a small difference in the inpaint code.
DDIM uses randn_like but I set a fixed seed instead.

I'm keeping it in because I'm sure if I remove it people are going to
complain.
2023-10-31 18:11:29 -04:00
comfyanonymous
1777b54d02 Sampling code changes.
apply_model in model_base now returns the denoised output.

This means that sampling_function now computes things on the denoised
output instead of the model output. This should make things more consistent
across current and future models.
2023-10-31 17:33:43 -04:00
tsone
23c5d17837 Added Bayer dithering to Quantize node. 2023-10-31 22:22:40 +01:00
comfyanonymous
c837a173fa Fix some memory issues in sub quad attention. 2023-10-30 15:30:49 -04:00
comfyanonymous
125b03eead Fix some OOM issues with split attention. 2023-10-30 13:14:11 -04:00
Jedrzej Kosinski
41b07ff8d7 Fix TAESD preview to only decode first latent, instead of all 2023-10-29 13:30:23 -05:00
comfyanonymous
a12cc05323 Add --max-upload-size argument, the default is 100MB. 2023-10-29 03:55:46 -04:00
comfyanonymous
aac8fc99d6 Cleanup webp import code a bit. 2023-10-28 12:24:50 -04:00
comfyanonymous
2a134bfab9 Fix checkpoint loader with config. 2023-10-27 22:13:55 -04:00
comfyanonymous
e60ca6929a SD1 and SD2 clip and tokenizer code is now more similar to the SDXL one. 2023-10-27 15:54:04 -04:00
comfyanonymous
6ec3f12c6e Support SSD1B model and make it easier to support asymmetric unets. 2023-10-27 14:45:15 -04:00
comfyanonymous
434ce25ec0 Restrict loading embeddings from embedding folders. 2023-10-27 02:54:13 -04:00
comfyanonymous
40963b5a16 Apply primitive nodes to graph before serializing workflow. 2023-10-26 19:52:41 -04:00
comfyanonymous
723847f6b3 Faster clip image processing. 2023-10-26 01:53:01 -04:00
comfyanonymous
a373367b0c Fix some OOM issues with split and sub quad attention. 2023-10-25 20:17:28 -04:00
comfyanonymous
7fbb217d3a Fix uni_pc returning noisy image when steps <= 3 2023-10-25 16:08:30 -04:00
Jedrzej Kosinski
3783cb8bfd change 'c_adm' to 'y' in ControlNet.get_control 2023-10-25 08:24:32 -05:00
comfyanonymous
d1d2fea806 Pass extra conds directly to unet. 2023-10-25 00:07:53 -04:00
comfyanonymous
036f88c621 Refactor to make it easier to add custom conds to models. 2023-10-24 23:31:12 -04:00
comfyanonymous
3fce8881ca Sampling code refactor to make it easier to add more conds. 2023-10-24 03:38:41 -04:00
comfyanonymous
5c65da312a Remove prints. 2023-10-23 23:39:22 -04:00
comfyanonymous
b935bea3a0 The frontend can now load workflows from webp exif. 2023-10-23 21:13:50 -04:00
pythongosssss
a92409c0ec Merge remote-tracking branch 'origin/master' into group-nodes 2023-10-23 16:35:44 +01:00
comfyanonymous
2ec6158e9e Call widget callback on value control to fix primitive node issue. 2023-10-22 23:38:18 -04:00
comfyanonymous
8594c8be4d Empty the cache when torch cache is more than 25% free mem. 2023-10-22 13:58:12 -04:00
pythongosssss
b440f86618 tidy 2023-10-22 14:47:05 +01:00
pythongosssss
32cdc7161d Fix aborting convert 2023-10-22 14:36:32 +01:00
pythongosssss
c5eec07207 Fix template nodes not being stored 2023-10-22 14:32:39 +01:00
pythongosssss
73cc92af77 Merge remote-tracking branch 'origin/master' into group-nodes 2023-10-22 14:20:23 +01:00
pythongosssss
bb4e65d4e1 Save group nodes to templates 2023-10-22 14:16:57 +01:00
comfyanonymous
8b65f5de54 attention_basic now works with hypertile. 2023-10-22 03:59:53 -04:00