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
comfyanonymous
b14fe05bf2
Fix PerpNeg node.
2024-04-05 11:46:54 -04:00
comfyanonymous
bc8bef3daa
Support for CosXL models.
2024-04-05 10:53:41 -04:00
comfyanonymous
897d5b6569
Fix object_patches_backup not being the same object across clones.
2024-04-05 00:22:44 -04:00
comfyanonymous
c618084a1c
Fix missing arguments in cfg_function.
2024-04-04 23:38:57 -04:00
comfyanonymous
50463b3e5a
Fix issue with get_model_object on patched model.
2024-04-04 23:01:02 -04:00
comfyanonymous
22462103f3
Fix model needing to be loaded on GPU to generate the sigmas.
2024-04-04 22:08:49 -04:00
comfyanonymous
125a62efe2
Add InstructPixToPixConditioning node.
2024-04-04 15:06:17 -04:00
comfyanonymous
d13e1a9139
Add DualCFGGuider used in IP2P models for example.
2024-04-04 14:57:44 -04:00
comfyanonymous
640f73d9ec
Add basic guider for models with no cfg.
2024-04-04 13:57:32 -04:00
comfyanonymous
58a02039bc
Make zero denoise a NOP.
2024-04-04 11:41:27 -04:00
comfyanonymous
1f511af362
Small cleanup.
2024-04-04 11:16:49 -04:00
comfyanonymous
0c89f0dab0
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
comfyanonymous
bcb4f07071
Refactor sampler code for more advanced sampler nodes part 2.
2024-04-04 01:26:41 -04:00
comfyanonymous
f9e7f0e695
Refactor sampling code for more advanced sampler nodes.
2024-04-03 22:09:51 -04:00
comfyanonymous
41f74d8e93
Fix saving text encoder in fp8.
2024-04-02 11:46:34 -04:00
comfyanonymous
1ba93001e4
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
comfyanonymous
f959eff2fa
--force-fp16 is no longer necessary on Mac.
2024-03-31 12:50:28 -04:00
comfyanonymous
284361ba73
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
comfyanonymous
207f045783
Add log to debug custom nodes that hang when imported.
2024-03-30 11:52:11 -04:00
comfyanonymous
56b08f7b30
Cleanup to support different types of inpaint models.
2024-03-29 14:44:13 -04:00
comfyanonymous
444caaaf7d
Switch prints to logging in folder_paths and add some extra debug.
2024-03-29 03:07:13 -04:00
comfyanonymous
cd0be2a31e
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
comfyanonymous
494bd7579e
Support SDXS 0.9
2024-03-27 23:58:58 -04:00
comfyanonymous
6cdb28091a
Make step on sharpen node smaller.
2024-03-27 01:28:31 -04:00
comfyanonymous
050f6ae8c8
Add Tesla GPUs to cuda malloc blacklist.
2024-03-26 23:09:28 -04:00
comfyanonymous
d97bcaea65
Fix test.
2024-03-26 04:07:30 -04:00
comfyanonymous
e0c8ff6f32
Increase the max resolution.
2024-03-26 04:00:53 -04:00
comfyanonymous
ec14272c0a
dora_scale support for lora file.
2024-03-25 18:09:23 -04:00
comfyanonymous
af7900cd79
Optimize memory unload strategy for more optimized performance.
2024-03-24 02:36:30 -04:00
comfyanonymous
cd92ad35a9
Move cleanup_models to improve performance.
2024-03-23 17:27:10 -04:00
comfyanonymous
614ef3351a
Add an example to use the SaveImageWebsocket node and enable it.
2024-03-22 12:56:48 -04:00
comfyanonymous
6b490edbab
Add inverse noise scaling function.
2024-03-21 14:49:11 -04:00
comfyanonymous
4e8d2577a9
Fix regression with lcm not working with batches.
2024-03-20 20:48:54 -04:00
comfyanonymous
2db9fdbacc
Fix regression with model merging.
2024-03-20 13:56:12 -04:00
comfyanonymous
1681937288
Don't unload model weights for non weight patches.
2024-03-20 02:27:58 -04:00
