4201181b35
Add ModelMergeSD1, ModelMergeSD2 and ModelMergeSDXL.
2024-04-09 04:31:14 -04:00
30abc324c2
Support properly saving CosXL checkpoints.
2024-04-08 00:36:22 -04:00
d644b6bcd8
Cleanup some more conditioning nodes.
2024-04-07 14:40:43 -04:00
c9fc242e2c
The middle prompt should be treated more as a negative prompt.
2024-04-07 14:34:43 -04:00
80bda6c163
Cleanup a few conditioning nodes.
2024-04-07 14:27:40 -04:00
0a03009808
Fix issue with controlnet models getting loaded multiple times.
2024-04-06 18:38:39 -04:00
de172f8be7
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
d8dea4cdb8
Fix DisableNoise node.
2024-04-05 21:36:23 -04:00
a7dd82e668
Fix copy paste issue with litegraph.
2024-04-05 14:59:05 -04:00
38ed2da2dd
Fix typo in lowvram patcher ( #3209 )
2024-04-05 12:02:13 -04:00
ea9ac9d30b
Fix PerpNeg node.
2024-04-05 11:46:54 -04:00
1088d1850f
Support for CosXL models.
2024-04-05 10:53:41 -04:00
41ed7e85ea
Fix object_patches_backup not being the same object across clones.
2024-04-05 00:22:44 -04:00
0f5768e038
Fix missing arguments in cfg_function.
2024-04-04 23:38:57 -04:00
1f4fc9ea0c
Fix issue with get_model_object on patched model.
2024-04-04 23:01:02 -04:00
1a0486bb96
Fix model needing to be loaded on GPU to generate the sigmas.
2024-04-04 22:08:49 -04:00
1f8d8e6c77
Add InstructPixToPixConditioning node.
2024-04-04 15:06:17 -04:00
5272fd4b03
Add DualCFGGuider used in IP2P models for example.
2024-04-04 14:57:44 -04:00
cfbf3be54b
Add basic guider for models with no cfg.
2024-04-04 13:57:32 -04:00
c6bd456c45
Make zero denoise a NOP.
2024-04-04 11:41:27 -04:00
fcfd2bdf8a
Small cleanup.
2024-04-04 11:16:49 -04:00
f117566299
SamplerCustomAdvanced node.
...
This node enables the creation of nodes to change the guider/denoiser and
the noise algorithm.
2024-04-04 01:32:25 -04:00
0542088ef8
Refactor sampler code for more advanced sampler nodes part 2.
2024-04-04 01:26:41 -04:00
57753c964a
Refactor sampling code for more advanced sampler nodes.
2024-04-03 22:09:51 -04:00
6c6a39251f
Fix saving text encoder in fp8.
2024-04-02 11:46:34 -04:00
e6482fbbfc
Refactor calc_cond_uncond_batch into calc_cond_batch.
...
calc_cond_batch can take an arbitrary amount of cond inputs.
Added a calc_cond_uncond_batch wrapper with a warning so custom nodes
won't break.
2024-04-01 18:07:47 -04:00
1306464538
--force-fp16 is no longer necessary on Mac.
2024-03-31 12:50:28 -04:00
575acb69e4
IP2P model loading support.
...
This is the code to load the model and inference it with only a text
prompt. This commit does not contain the nodes to properly use it with an
image input.
This supports both the original SD1 instructpix2pix model and the
diffusers SDXL one.
2024-03-31 03:10:28 -04:00
96b4c757cf
Add log to debug custom nodes that hang when imported.
2024-03-30 11:52:11 -04:00
94a5a67c32
Cleanup to support different types of inpaint models.
2024-03-29 14:44:13 -04:00
9bf6061dfc
Switch prints to logging in folder_paths and add some extra debug.
2024-03-29 03:07:13 -04:00
5d8898c056
Fix some performance issues with weight loading and unloading.
...
Lower peak memory usage when changing model.
Fix case where model weights would be unloaded and reloaded.
2024-03-28 18:04:42 -04:00
327ca1313d
Support SDXS 0.9
2024-03-27 23:58:58 -04:00
8ae1e4d125
Make step on sharpen node smaller.
2024-03-27 01:28:31 -04:00
2f93b91646
Add Tesla GPUs to cuda malloc blacklist.
2024-03-26 23:09:28 -04:00
c9673926fb
Fix test.
2024-03-26 04:07:30 -04:00
11838e60f4
Increase the max resolution.
2024-03-26 04:00:53 -04:00
ae77590b4e
dora_scale support for lora file.
2024-03-25 18:09:23 -04:00
c6de09b02e
Optimize memory unload strategy for more optimized performance.
2024-03-24 02:36:30 -04:00
6a32c06f06
Move cleanup_models to improve performance.
2024-03-23 17:27:10 -04:00
a28a9dc836
Add an example to use the SaveImageWebsocket node and enable it.
2024-03-22 12:56:48 -04:00
0624838237
Add inverse noise scaling function.
2024-03-21 14:49:11 -04:00
5d875d77fe
Fix regression with lcm not working with batches.
2024-03-20 20:48:54 -04:00
4b9005e949
Fix regression with model merging.
2024-03-20 13:56:12 -04:00
c18a203a8a
Don't unload model weights for non weight patches.
2024-03-20 02:27:58 -04:00
150a3e946f
Make LCM sampler use the model noise scaling function.
2024-03-20 01:35:59 -04:00
d14bdb1896
Revert, NOTE: this will be removed again soon please fix your nodes.
2024-03-19 11:17:49 -04:00
0c55f16c9e
Remove code that should be useless now.
2024-03-19 09:47:14 -04:00
40e124c6be
SV3D support.
2024-03-18 16:54:13 -04:00
0b78213bda
Fix neg scale step.
2024-03-18 15:51:23 -04:00
comfyanonymous
Gorka Eguileor
kk-89