RomanNum3ral
/
ComfyUI
mirror of https://github.com/Comfy-Org/ComfyUI.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
5,089 Commits 370 Branches 178 Tags 1.9 GiB
Commit Graph

26 Commits

Author SHA1 Message Date
octo-patch ce6b8b72de fix: clone latent before TAESD preview decode to prevent corruption (fixes #13366) 
The TAESD preview decoders (TAESDPreviewerImpl and TAEHVPreviewerImpl) were
passing tensor views (slices) of x0 directly to the decoder. This allowed the
decoder's internal operations to potentially modify the original latent in-place,
corrupting the midsampling latent.

The fix clones the sliced tensor before passing it to the decoder, ensuring the
original x0 is never affected by any in-place operations within the preview decode
path.

This specifically addresses the case where lighttaew2_1.safetensors (WanVAE) is
used as the TAESD preview decoder for models using the Wan21 latent format (e.g.,
QwenImage), where the full VAE decode pipeline could write back to the input slice.
 2026-04-13 12:39:51 +08:00
Jukka Seppänen 3365ad18a5
Support LTX2 tiny vae (taeltx_2) (#11929) 2026-01-21 23:03:51 -05:00
Dr.Lt.Data dbd330454a
feat(preview): add per-queue live preview method override (#11261) 
- Add set_preview_method() to override live preview method per queue item
- Read extra_data.preview_method from /prompt request
- Support values: taesd, latent2rgb, none, auto, default
- "default" or unset uses server's CLI --preview-method setting
- Add 44 tests (37 unit + 7 E2E)
 2025-12-15 15:57:39 -08:00
Jukka Seppänen b907085709
Support video tiny VAEs (#10884) 
* Support video tiny VAEs

* lighttaew scaling fix

* Also support video taes in previews

Only first frame for now as live preview playback is currently only available through VHS custom nodes.

* Support Wan 2.1 lightVAE

* Relocate elif block and set Wan VAE dim directly without using pruning rate for lightvae
 2025-11-28 19:40:19 -05:00
comfyanonymous f16219e3aa
Add cheap latent preview for flux 2. (#10907) 
Thank you to the person who calculated them. You saved me a percent of my
time.
 2025-11-26 04:00:43 -05:00
Bradley Reynolds 1210d094c7
Convert `latents_ubyte` to 8-bit unsigned int before converting to CPU (#6300) 
* Convert latents_ubyte to 8-bit unsigned int before converting to CPU

* Only convert to unint8 if directml_enabled
 2025-01-28 08:22:54 -05:00
Chenlei Hu 0fd4e6c778
Lint unused import (#5973) 
* Lint unused import

* nit

* Remove unused imports

* revert fix_torch import

* nit
 2024-12-09 15:24:39 -05:00
comfyanonymous bdeb1c171c Fast previews for mochi. 2024-11-10 03:39:35 -05:00
comfyanonymous a9e459c2a4 Use torch.nn.functional.linear in RGB preview code. 
Add an optional bias to the latent RGB preview code.
 2024-09-29 11:27:49 -04:00
Silver f067ad15d1
Make live preview size a configurable launch argument (#4649) 
* Make live preview size a configurable launch argument

* Remove import from testing phase

* Update cli_args.py
 2024-09-03 19:16:38 -04:00
Dr.Lt.Data df7db0e027
support TAESD3 (#3738) 2024-06-16 02:03:53 -04:00
comfyanonymous 04b308229e Small refactor of preview code. 2024-05-31 11:18:37 -04:00
comfyanonymous 58c9838274 Speed up TAESD preview. 2024-05-24 02:37:57 -04:00
comfyanonymous 6c23854f54 Fix OSX latent2rgb previews. 2024-05-22 13:56:28 -04:00
comfyanonymous 4ae1515f14 Slightly faster latent2rgb previews. 2024-05-19 17:42:35 -04:00
comfyanonymous f37a47110b Make --preview-method auto default to the fast latent2rgb previews. 2024-05-19 11:45:36 -04:00
comfyanonymous 03f4cfb7cd Replace more prints with logging. 2024-03-11 00:58:49 -04:00
comfyanonymous cd4fc77d5f Add taesd and taesdxl to VAELoader node. 
They will show up if both the taesd_encoder and taesd_decoder or taesdxl
model files are present in the models/vae_approx directory.
 2023-11-21 12:54:19 -05:00
Jedrzej Kosinski 41b07ff8d7 Fix TAESD preview to only decode first latent, instead of all 2023-10-29 13:30:23 -05:00
Yukimasa Funaoka 9eb621c95a
Supports TAESD models in safetensors format 2023-10-10 13:21:44 +09:00
comfyanonymous bf3fc2f1b7 Refactor sampling related code. 2023-09-27 16:45:22 -04:00
comfyanonymous 61b1f67734 Support models without previews. 2023-09-16 12:59:54 -04:00
comfyanonymous ccb6b70de1 Move image encoding outside of sampling loop for better preview perf. 2023-07-19 18:06:58 -04:00
Dr.Lt.Data 9caab9380d
fix: Image.ANTIALIAS is no longer available. (#847) 
* modify deprecated api call

* prevent breaking old Pillow users

* change LANCZOS to BILINEAR
 2023-07-08 02:36:48 -04:00
comfyanonymous cef6aa62b2 Add support for TAESD decoder for SDXL. 2023-06-25 02:38:14 -04:00
comfyanonymous a3a713b6c5 Refactor previews into one command line argument. 
Clean up a few things.
 2023-06-06 02:13:05 -04:00