c59fe9f254
Support VAE without quant_conv.
7 months ago
719fb2c81d
Add basic PAG node.
7 months ago
258dbc06c3
Fix some memory related issues.
7 months ago
58812ab8ca
Support SDXS 512 model.
7 months ago
831511a1ee
Fix issue with sampling_settings persisting across models.
7 months ago
30abc324c2
Support properly saving CosXL checkpoints.
7 months ago
0a03009808
Fix issue with controlnet models getting loaded multiple times.
8 months ago
38ed2da2dd
Fix typo in lowvram patcher ( #3209 )
8 months ago
1088d1850f
Support for CosXL models.
8 months ago
41ed7e85ea
Fix object_patches_backup not being the same object across clones.
8 months ago
0f5768e038
Fix missing arguments in cfg_function.
8 months ago
1f4fc9ea0c
Fix issue with get_model_object on patched model.
8 months ago
1a0486bb96
Fix model needing to be loaded on GPU to generate the sigmas.
8 months ago
c6bd456c45
Make zero denoise a NOP.
8 months ago
fcfd2bdf8a
Small cleanup.
8 months ago
0542088ef8
Refactor sampler code for more advanced sampler nodes part 2.
8 months ago
57753c964a
Refactor sampling code for more advanced sampler nodes.
8 months ago
6c6a39251f
Fix saving text encoder in fp8.
8 months ago
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
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
94a5a67c32
Cleanup to support different types of inpaint models.
8 months ago
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
327ca1313d
Support SDXS 0.9
8 months ago
ae77590b4e
dora_scale support for lora file.
8 months ago
c6de09b02e
Optimize memory unload strategy for more optimized performance.
8 months ago
0624838237
Add inverse noise scaling function.
8 months ago
5d875d77fe
Fix regression with lcm not working with batches.
8 months ago
4b9005e949
Fix regression with model merging.
8 months ago
c18a203a8a
Don't unload model weights for non weight patches.
8 months ago
150a3e946f
Make LCM sampler use the model noise scaling function.
8 months ago
40e124c6be
SV3D support.
8 months ago
cacb022c4a
Make saved SD1 checkpoints match more closely the official one.
8 months ago
d7897fff2c
Move cascade scale factor from stage_a to latent_formats.py
8 months ago
f2fe635c9f
SamplerDPMAdaptative node to test the different options.
8 months ago
448d9263a2
Fix control loras breaking.
8 months ago
db8b59ecff
Lower memory usage for loras in lowvram mode at the cost of perf.
8 months ago
2a813c3b09
Switch some more prints to logging.
8 months ago
0ed72befe1
Change log levels.
...
Logging level now defaults to info. --verbose sets it to debug.
8 months ago
65397ce601
Replace prints with logging and add --verbose argument.
8 months ago
5f60ee246e
Support loading the sr cascade controlnet.
9 months ago
03e6e81629
Set upscale algorithm to bilinear for stable cascade controlnet.
9 months ago
03e83bb5d0
Support stable cascade canny controlnet.
9 months ago
10860bcd28
Add compression_ratio to controlnet code.
9 months ago
478f71a249
Remove useless check.
9 months ago
12c1080ebc
Simplify differential diffusion code.
9 months ago
727021bdea
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.
9 months ago
1abf8374ec
utils.set_attr can now be used to set any attribute.
...
The old set_attr has been renamed to set_attr_param.
9 months ago
dce3555339
Add some tesla pascal GPUs to the fp16 working but slower list.
9 months ago
51df846598
Let conditioning specify custom concat conds.
9 months ago
9f71e4b62d
Let model patches patch sub objects.
9 months ago
comfyanonymous
kk-89
Shiimizu