2160 Commits

Author SHA1 Message Date
comfyanonymous
e3584eacd1 Only set LOAD_TRUNCATED_IMAGES when if the Image open fails.
Document which PIL issues this works around.
2024-05-04 03:51:03 -04:00
shawnington
54734013e9 Fixed Issue with LoadImage node when loading PNG files with embedded ICC profiles. (#3316)
* Fix issue with how PIL loads small PNG files nodes.py

Added flag to prevent ValueError: Decompressed Data Too Large
when loading PNG images with large meta data such as large embedded color profiles

* Update LoadImage node to fix error when loading PNG's in nodes.py

Fixed Value Error: Decompressed Data Too Large thrown by PIL when attempting to opening PNG files with large embedded ICC colorspaces by setting the follow flag to true when loading png images:  ImageFile.LOAD_TRUNCATED_IMAGES = True

* Update node_helpers.py to include open_image helper function

open_image includes try except to catch Pillow Value Errors that occur when large ICC profiles are embedded in images.

* Update LoadImage node to use open_image helper function inplace of Image.open

open_image helper function in node_helpers.py  fixes a Pillow error when attempting to open images with large embedded ICC profiles by adding an exception handler to load the image with truncated meta data if regular loading is not possible.
2024-05-04 03:32:41 -04:00
comfyanonymous
f8dfa67f3a Fix potential issues with the int rounding fix. 2024-05-03 05:49:21 -04:00
comfyanonymous
02b6774cdc Fix int widgets rounding. 2024-05-02 03:34:19 -04:00
Simon Lui
87e7b35146 Change torch.xpu to ipex.optimize, xpu device initialization and remove workaround for text node issue from older IPEX. (#3388) 2024-05-02 03:26:50 -04:00
comfyanonymous
b04267ce30 Fix some edge cases with samplers and arrays with a single sigma. 2024-05-01 17:05:30 -04:00
comfyanonymous
b7d06aa5a2 Don't load the model in SDTurboScheduler 2024-05-01 16:57:10 -04:00
comfyanonymous
95e80c5df1 Workaround xformers bug. 2024-04-30 21:23:40 -04:00
Garrett Sutula
533ddd78a0 Add TLS Support (#3312)
* Add TLS Support

* Add to readme

* Add guidance for windows users on generating certificates

* Add guidance for windows users on generating certificates

* Fix typo
2024-04-30 20:17:02 -04:00
comfyanonymous
ce6414502f Update Readme. 2024-04-30 20:11:34 -04:00
comfyanonymous
0b60bc8854 Add a SamplerLCMUpscale node.
This sampler is an LCM sampler that upscales the latent during sampling.

It can be used to generate at a higher resolution with an LCM model very
quickly.

To try it use it with a basic 5 step LCM workflow with scale_ratio 1.5 or
2.0
2024-04-29 20:00:47 -04:00
comfyanonymous
45d2d7aa6d Add some nodes to multiply the attention in UNet and Clip models. 2024-04-28 13:03:43 -04:00
comfyanonymous
a0b0f20ac5 Add a denoise value to AlignYourStepsScheduler. 2024-04-27 00:48:41 -04:00
comfyanonymous
b3ace457cb Update command for AMD stable pytorch install in README. 2024-04-26 15:44:12 -04:00
Jedrzej Kosinski
7a37c3088d Fix error when more cond masks passed in than batch size (#3353) 2024-04-26 12:51:12 -04:00
comfyanonymous
28cb4e1b8b Free more vram for upscale models. 2024-04-25 17:04:19 -04:00
comfyanonymous
e7cd70ed48 Don't init a VAE model when there are no VAE weights. 2024-04-24 09:20:31 -04:00
comfyanonymous
108d37e283 Increase max lora strength to 100.0 2024-04-23 13:07:39 -04:00
Pam
6056ab1862 Increase sigma_min/sigma_max range for custom schedulers (#3317) 2024-04-23 09:40:10 -04:00
comfyanonymous
bb829e58e4 Free some memory before loading upscale models. 2024-04-22 18:51:15 -04:00
comfyanonymous
edc0033c3a Speed up Sharpen node. 2024-04-21 09:02:06 -04:00
comfyanonymous
fb91cd8220 Implement Align Your Steps as a AlignYourStepsScheduler node. 2024-04-20 04:34:12 -04:00
comfyanonymous
ab4ac5d9b7 Faster blur. 2024-04-19 03:52:02 -04:00
comfyanonymous
d5efb0cf00 Sync some minor changes from the other repo. 2024-04-19 03:43:09 -04:00
comfyanonymous
918d7520c3 Support VAE without quant_conv. 2024-04-18 21:05:33 -04:00
Torbjörn Lönnemark
fbe9ae1466 Improve node input/widget conversion sub-menus (#3281)
* Make input/widget conversion sub-menus optional

* Improve input/widget conversion sub-menu text

- Fix incorrect text for conversion from widget to input, previously it
  effectively said "convert input to input"
- Use "input" instead of "🔘".  The former is clearer and consistent
  with the rest of the application.
- Use title case (consistent with the rest of the menu entries).
- Strip the trailing periods. There is already a visual indicator for
  sub-menus, and no other sub-menus use trailing periods.
2024-04-18 16:41:23 -04:00
comfyanonymous
6482ab3346 Fix annoying float issue causing the value to be rounded to above the max. 2024-04-17 17:34:02 -04:00
Dr.Lt.Data
1a676acbbb Fixed an issue where the main menu disappears intermittently as the coordinates become negative. (#3269) 2024-04-17 16:36:49 -04:00
comfyanonymous
c3970a24a9 Add a helpful warning for links that don't point anywhere. 2024-04-17 12:28:05 -04:00
comfyanonymous
1d7643bb4b Implement PerpNeg as a guider. 2024-04-16 02:57:34 -04:00
comfyanonymous
c02882377a This can be removed since PAG doesn't use the uncond. 2024-04-15 12:14:00 -04:00
comfyanonymous
0c38c2d09c Add basic PAG node. 2024-04-14 23:49:50 -04:00
comfyanonymous
982b8e2276 Fix some memory related issues. 2024-04-14 12:08:58 -04:00
comfyanonymous
d749f0c0eb Don't make dynamicPrompts the default on multiline string inputs.
This should be less confusing to those who want to use multiline input
without them.
2024-04-13 16:18:00 -04:00
comfyanonymous
4c7f73bb85 Support SDXS 512 model. 2024-04-12 22:12:35 -04:00
comfyanonymous
ca75fe6eb1 Fix tests. 2024-04-12 20:02:53 -04:00
NyaamZ
b7758d16ae change Convert.. input (#3246) 2024-04-12 17:02:17 -04:00
comfyanonymous
413ca557f7 Add some colors to SamplerCustom links.
If you don't like them I am open to a PR.
2024-04-11 22:43:05 -04:00
comfyanonymous
312b19ea00 Add an AddNoise node to add noise depending on the sigma. 2024-04-10 23:40:31 -04:00
comfyanonymous
6334ac514b Fix issue with sampling_settings persisting across models. 2024-04-09 23:20:43 -04:00
comfyanonymous
02ed89f43c Add ModelMergeSD1, ModelMergeSD2 and ModelMergeSDXL. 2024-04-09 04:31:14 -04:00
comfyanonymous
ef332e5355 Support properly saving CosXL checkpoints. 2024-04-08 00:36:22 -04:00
comfyanonymous
e70f01e651 Cleanup some more conditioning nodes. 2024-04-07 14:40:43 -04:00
comfyanonymous
d3d009c5a9 The middle prompt should be treated more as a negative prompt. 2024-04-07 14:34:43 -04:00
comfyanonymous
970fcffcb9 Cleanup a few conditioning nodes. 2024-04-07 14:27:40 -04:00
comfyanonymous
d93e3f1991 Fix issue with controlnet models getting loaded multiple times. 2024-04-06 18:38:39 -04:00
Gorka Eguileor
25c81b10e5 Improve A1111 metadata parsing (#3216)
* A1111 import: Set VAE name

This patch sets the VAE name for the `VAELoader` when present in the png
metadata.

* A1111 import: Skip all hashes

When importing from A1111 the parsing assumes that values of a key will
never contain a ":", which is not correct.

There are 2 cases where we can have ":" in the value:

- Inside a string. E.g.:
  Lora hashes: "xl_more_art-full_v1: fe3b4816be83, add-detail-xl: 9c783c8ce46c"

- When the value is a json dictionary. E.g.:
  Hashes: {"vae": "63aeecb90f", "embed:negativeXL_D": "fff5d51ab6"}

This patch changes how we parse the metadata to take those 2 cases into
account and also skips the following additional keys that are present in
some Forge images:

- Version
- VAE hash
- TI hashes
- Lora hashes
- Hashes

* A1111 import: Parse Hires steps

This patch parses the `Hires steps` parameter that is part of the High
Resolution Upscale configuration when it  is present, and fallbacks to
the one from the `samplerNode` (like the code currently does) if it's
not present.
2024-04-06 12:10:17 -04:00
comfyanonymous
0e474e1622 Fix DisableNoise node. 2024-04-05 21:36:23 -04:00
comfyanonymous
5b40c3290f Fix copy paste issue with litegraph. 2024-04-05 14:59:05 -04:00
kk-89
a9c852912f Fix typo in lowvram patcher (#3209) 2024-04-05 12:02:13 -04:00