comfyanonymous
|
cec2bda050
|
Update the standalone package updater so it can self update.
|
2024-02-26 08:51:16 -05:00 |
|
comfyanonymous
|
c8556665f0
|
Make return_projected_pooled setable from the __init__
|
2024-02-25 14:49:13 -05:00 |
|
comfyanonymous
|
3a1175858f
|
Support loading old CLIP models saved with CLIPSave.
|
2024-02-25 08:29:12 -05:00 |
|
僵尸浩
|
e6d639a33c
|
disable follow_symlinks in static serving for security reason (#2902)
|
2024-02-25 07:43:26 -05:00 |
|
comfyanonymous
|
d7f18fae37
|
Add example for how to use WEB_DIRECTORY to add frontend extensions.
|
2024-02-25 07:34:22 -05:00 |
|
comfyanonymous
|
766b45c2c1
|
Always return unprojected pooled output for gligen.
|
2024-02-25 07:33:13 -05:00 |
|
comfyanonymous
|
9e5c5a0ad3
|
Move text projection into the CLIP model code.
Fix issue with not loading the SSD1B clip correctly.
|
2024-02-25 01:41:08 -05:00 |
|
comfyanonymous
|
c2c8c2e398
|
Support text encoder text_projection in lora.
|
2024-02-24 23:50:46 -05:00 |
|
comfyanonymous
|
011603557d
|
Support lora keys with lora_prior_unet_ and lora_prior_te_
|
2024-02-23 12:21:20 -05:00 |
|
logtd
|
5dfd39f190
|
Fix model and cond transformer options merge
|
2024-02-23 01:19:43 -07:00 |
|
comfyanonymous
|
8d2b46bfbe
|
Cleanup uni_pc inpainting.
This causes some small changes to the uni pc inpainting behavior but it
seems to improve results slightly.
|
2024-02-23 02:39:35 -05:00 |
|
comfyanonymous
|
bc2422090b
|
Merge branch 'patch-1' of https://github.com/feffy380/ComfyUI
|
2024-02-22 16:23:50 -05:00 |
|
Rick Love
|
7967dc360e
|
FIX recursive_will_execute performance (simple ~300x performance increase} (#2852)
* FIX recursive_will_execute performance
* Minimize code changes
* memo must be created outside lambda
|
2024-02-21 20:21:24 -05:00 |
|
comfyanonymous
|
a25fa937dc
|
ModelSamplingDiscrete: x0 model support that predict a denoised image.
|
2024-02-21 08:05:43 -05:00 |
|
feffy380
|
a5a21e526e
|
Fix Perp-Neg math
adjust perp-neg implementation to match the paper
|
2024-02-21 10:33:03 +01:00 |
|
comfyanonymous
|
1fe5f6446f
|
Add some latent2rgb matrices for previews.
|
2024-02-20 10:57:24 -05:00 |
|
comfyanonymous
|
ecdec096f3
|
Pass pooled CLIP to stage b.
|
2024-02-20 04:24:45 -05:00 |
|
comfyanonymous
|
084f3a1561
|
Align simple scheduling closer to official stable cascade scheduler.
|
2024-02-20 04:24:39 -05:00 |
|
comfyanonymous
|
62c8d15a4f
|
Add to Readme that stable cascade is supported.
|
2024-02-19 13:41:55 -05:00 |
|
comfyanonymous
|
1b2e67827f
|
Node to make stable cascade image to image easier.
|
2024-02-19 13:36:20 -05:00 |
|
comfyanonymous
|
f4e74ae786
|
Enable fp16 by default on mps.
|
2024-02-19 12:00:48 -05:00 |
|
comfyanonymous
|
7ea7ac1414
|
Remove print.
|
2024-02-19 11:47:26 -05:00 |
|
comfyanonymous
|
f940826501
|
Support Stable Cascade in checkpoint format.
|
2024-02-19 11:20:48 -05:00 |
|
comfyanonymous
|
4575a1c500
|
Some cleanups to how the text encoders are loaded.
|
2024-02-19 10:46:30 -05:00 |
|
comfyanonymous
|
cb8f02a4a9
|
Larger range for min/max compression for StableCascade_EmptyLatentImage.
|
2024-02-19 08:59:53 -05:00 |
|
comfyanonymous
|
1067555cae
|
Forgot to commit this.
|
2024-02-19 04:25:46 -05:00 |
|
comfyanonymous
|
217e660839
|
Support loading the Stable Cascade effnet and previewer as a VAE.
The effnet can be used to encode images for img2img with Stage C.
|
2024-02-19 04:10:01 -05:00 |
|
comfyanonymous
|
d55c5b2398
|
Merge branch 'iTXt-png-metadata-support' of https://github.com/shiimizu/ComfyUI
|
2024-02-18 23:44:58 -05:00 |
|
shiimizu
|
42458f34bc
|
Support additional PNG info.
|
2024-02-18 17:57:53 -08:00 |
|
comfyanonymous
|
ad760b32de
|
Fix gligen lowvram mode.
|
2024-02-18 02:20:23 -05:00 |
|
comfyanonymous
|
3518d94368
|
Add ModelSamplingStableCascade to control the shift sampling parameter.
shift is 2.0 by default on Stage C and 1.0 by default on Stage B.
|
2024-02-18 00:55:23 -05:00 |
|
comfyanonymous
|
681300661a
|
Fix attention masks properly for multiple batches.
|
2024-02-17 16:15:18 -05:00 |
|
comfyanonymous
|
809b7f0b78
|
fp8 weight support for Stable Cascade.
|
2024-02-17 15:27:31 -05:00 |
|
comfyanonymous
|
511e70ab62
|
Fix attention mask batch size in some attention functions.
|
2024-02-17 15:22:21 -05:00 |
|
comfyanonymous
|
4a9216bca3
|
Properly fix attention masks in CLIP with batches.
|
2024-02-17 12:13:13 -05:00 |
|
comfyanonymous
|
8d4def2e89
|
Implement shift schedule for cascade stage C.
|
2024-02-17 11:38:47 -05:00 |
|
comfyanonymous
|
cabdbc2529
|
Manual cast for bf16 on older GPUs.
|
2024-02-17 09:01:17 -05:00 |
|
comfyanonymous
|
b527789f52
|
Fix clip attention mask issues on some hardware.
|
2024-02-17 07:53:52 -05:00 |
|
comfyanonymous
|
73407209f5
|
Make Stable Cascade work on old pytorch 2.0
|
2024-02-17 00:42:30 -05:00 |
|
comfyanonymous
|
56db0bef1e
|
Support Stable Cascade Stage B lite.
|
2024-02-16 23:41:23 -05:00 |
|
comfyanonymous
|
b3c820556b
|
Make --force-fp32 disable loading models in bf16.
|
2024-02-16 23:01:54 -05:00 |
|
comfyanonymous
|
b102d65c41
|
StableCascade CLIP model support.
|
2024-02-16 13:29:04 -05:00 |
|
comfyanonymous
|
e5a0f735be
|
Stable Cascade Stage B.
|
2024-02-16 13:02:03 -05:00 |
|
comfyanonymous
|
deebc95781
|
Stable Cascade Stage C.
|
2024-02-16 10:55:08 -05:00 |
|
comfyanonymous
|
ce56ca3f9d
|
Stable Cascade Stage A.
|
2024-02-16 06:30:39 -05:00 |
|
comfyanonymous
|
975dcd133a
|
Merge branch 'batch-number-in-filename' of https://github.com/freakabcd/ComfyUI
|
2024-02-16 05:45:48 -05:00 |
|
comfyanonymous
|
a3ada6af3b
|
Small refactor of is_device_* functions.
|
2024-02-15 21:10:10 -05:00 |
|
comfyanonymous
|
a48c4f8a80
|
Add a disabled SaveImageWebsocket custom node.
This node can be used to efficiently get images without saving them to
disk when using ComfyUI as a backend.
|
2024-02-14 03:01:25 -05:00 |
|
comfyanonymous
|
0fc2468c50
|
Don't init the CLIP model when the checkpoint has no CLIP weights.
|
2024-02-13 00:01:08 -05:00 |
|
comfyanonymous
|
7b608054c8
|
Add ImageFromBatch.
|
2024-02-12 12:46:15 -05:00 |
|