comfyanonymous
d644b6bcd8
Cleanup some more conditioning nodes.
7 months ago
comfyanonymous
c9fc242e2c
The middle prompt should be treated more as a negative prompt.
7 months ago
comfyanonymous
80bda6c163
Cleanup a few conditioning nodes.
7 months ago
comfyanonymous
0a03009808
Fix issue with controlnet models getting loaded multiple times.
8 months ago
Gorka Eguileor
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.
8 months ago
comfyanonymous
d8dea4cdb8
Fix DisableNoise node.
8 months ago
comfyanonymous
a7dd82e668
Fix copy paste issue with litegraph.
8 months ago
kk-89
38ed2da2dd
Fix typo in lowvram patcher ( #3209 )
8 months ago
comfyanonymous
ea9ac9d30b
Fix PerpNeg node.
8 months ago
comfyanonymous
1088d1850f
Support for CosXL models.
8 months ago
comfyanonymous
41ed7e85ea
Fix object_patches_backup not being the same object across clones.
8 months ago
comfyanonymous
0f5768e038
Fix missing arguments in cfg_function.
8 months ago
comfyanonymous
1f4fc9ea0c
Fix issue with get_model_object on patched model.
8 months ago
comfyanonymous
1a0486bb96
Fix model needing to be loaded on GPU to generate the sigmas.
8 months ago
comfyanonymous
1f8d8e6c77
Add InstructPixToPixConditioning node.
8 months ago
comfyanonymous
5272fd4b03
Add DualCFGGuider used in IP2P models for example.
8 months ago
comfyanonymous
cfbf3be54b
Add basic guider for models with no cfg.
8 months ago
comfyanonymous
c6bd456c45
Make zero denoise a NOP.
8 months ago
comfyanonymous
fcfd2bdf8a
Small cleanup.
8 months ago
comfyanonymous
f117566299
SamplerCustomAdvanced node.
...
This node enables the creation of nodes to change the guider/denoiser and
the noise algorithm.
8 months ago
comfyanonymous
0542088ef8
Refactor sampler code for more advanced sampler nodes part 2.
8 months ago
comfyanonymous
57753c964a
Refactor sampling code for more advanced sampler nodes.
8 months ago
comfyanonymous
6c6a39251f
Fix saving text encoder in fp8.
8 months ago
comfyanonymous
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.
8 months ago
comfyanonymous
1306464538
--force-fp16 is no longer necessary on Mac.
8 months ago
comfyanonymous
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.
8 months ago
comfyanonymous
96b4c757cf
Add log to debug custom nodes that hang when imported.
8 months ago
comfyanonymous
94a5a67c32
Cleanup to support different types of inpaint models.
8 months ago
comfyanonymous
9bf6061dfc
Switch prints to logging in folder_paths and add some extra debug.
8 months ago
comfyanonymous
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.
8 months ago
comfyanonymous
327ca1313d
Support SDXS 0.9
8 months ago
comfyanonymous
8ae1e4d125
Make step on sharpen node smaller.
8 months ago
comfyanonymous
2f93b91646
Add Tesla GPUs to cuda malloc blacklist.
8 months ago
comfyanonymous
c9673926fb
Fix test.
8 months ago
comfyanonymous
11838e60f4
Increase the max resolution.
8 months ago
comfyanonymous
ae77590b4e
dora_scale support for lora file.
8 months ago
comfyanonymous
c6de09b02e
Optimize memory unload strategy for more optimized performance.
8 months ago
comfyanonymous
6a32c06f06
Move cleanup_models to improve performance.
8 months ago
comfyanonymous
a28a9dc836
Add an example to use the SaveImageWebsocket node and enable it.
8 months ago
comfyanonymous
0624838237
Add inverse noise scaling function.
8 months ago
comfyanonymous
5d875d77fe
Fix regression with lcm not working with batches.
8 months ago
comfyanonymous
4b9005e949
Fix regression with model merging.
8 months ago
comfyanonymous
c18a203a8a
Don't unload model weights for non weight patches.
8 months ago
comfyanonymous
150a3e946f
Make LCM sampler use the model noise scaling function.
8 months ago
comfyanonymous
d14bdb1896
Revert, NOTE: this will be removed again soon please fix your nodes.
8 months ago
comfyanonymous
0c55f16c9e
Remove code that should be useless now.
8 months ago
comfyanonymous
40e124c6be
SV3D support.
8 months ago
comfyanonymous
0b78213bda
Fix neg scale step.
8 months ago
comfyanonymous
b1a16d4500
Fix stable cascade img2img not working with all resolutions.
8 months ago
comfyanonymous
cacb022c4a
Make saved SD1 checkpoints match more closely the official one.
8 months ago