comfyanonymous
03ccdd76a7
Simplify differential diffusion code.
2024-03-03 15:34:42 -05:00
Shiimizu
8363203d85
Implement Differential Diffusion ( #2876 )
...
* Implement Differential Diffusion
* Cleanup.
* Fix.
* Masks should be applied at full strength.
* Fix colors.
* Register the node.
* Cleaner code.
* Fix issue with getting unipc sampler.
* Adjust thresholds.
* Switch to linear thresholds.
* Only calculate nearest_idx on valid thresholds.
2024-03-03 15:34:13 -05:00
comfyanonymous
e7fb76e67b
utils.set_attr can now be used to set any attribute.
...
The old set_attr has been renamed to set_attr_param.
2024-03-02 17:27:23 -05:00
comfyanonymous
8726a79de9
Add some tesla pascal GPUs to the fp16 working but slower list.
2024-03-02 17:16:31 -05:00
comfyanonymous
e4c40b647b
Let conditioning specify custom concat conds.
2024-03-02 11:44:06 -05:00
comfyanonymous
b5931a324c
Let model patches patch sub objects.
2024-03-02 11:43:27 -05:00
comfyanonymous
bd39d6bfd6
Cleanup: Use sampling noise scaling function for inpainting.
2024-03-01 14:24:41 -05:00
comfyanonymous
5af225ffd9
Move noise scaling to object with sampling math.
2024-03-01 12:54:38 -05:00
comfyanonymous
2e622719d7
Allow image_only_indicator to be None.
2024-02-29 13:11:30 -05:00
comfyanonymous
79e83f92e8
Koala 700M and 1B support.
...
Use the UNET Loader node to load the unet file to use them.
2024-02-28 12:10:11 -05:00
comfyanonymous
51125444a3
Remove duplicate text_projection key from some saved models.
2024-02-28 03:57:41 -05:00
comfyanonymous
4a76090e6a
Auto detect playground v2.5 model.
2024-02-27 18:03:03 -05:00
comfyanonymous
0bd8fc1e4d
Playground V2.5 support with ModelSamplingContinuousEDM node.
...
Use ModelSamplingContinuousEDM with edm_playground_v2.5 selected.
2024-02-27 15:12:33 -05:00
comfyanonymous
87ba3045a4
Make XL checkpoints save in a more standard format.
2024-02-27 02:07:40 -05:00
comfyanonymous
b80c33e2f3
Make the text projection saved in the checkpoint the right format.
2024-02-27 01:52:23 -05:00
comfyanonymous
13fb082928
Add a min_length property to tokenizer class.
2024-02-26 21:36:37 -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
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
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
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
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
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
a3ada6af3b
Small refactor of is_device_* functions.
2024-02-15 21:10:10 -05:00
