comfyanonymous
056e5545ff
Don't try to get vram from xpu or cuda when directml is enabled.
2 years ago
comfyanonymous
2ca934f7d4
You can now select the device index with: --directml id
...
Like this for example: --directml 1
2 years ago
comfyanonymous
3baded9892
Basic torch_directml support. Use --directml to use it.
2 years ago
comfyanonymous
5a971cecdb
Add callback to sampler function.
...
Callback format is: callback(step, x0, x)
2 years ago
comfyanonymous
aa57136dae
Some fixes to the batch masks PR.
2 years ago
comfyanonymous
c50208a703
Refactor more code to sample.py
2 years ago
comfyanonymous
7983b3a975
This is cleaner this way.
2 years ago
BlenderNeko
0b07b2cc0f
gligen tuple
2 years ago
BlenderNeko
d9b1595f85
made sample functions more explicit
2 years ago
BlenderNeko
5818539743
add docstrings
2 years ago
BlenderNeko
2a09e2aa27
refactor/split various bits of code for sampling
2 years ago
comfyanonymous
5282f56434
Implement Linear hypernetworks.
...
Add a HypernetworkLoader node to use hypernetworks.
2 years ago
comfyanonymous
6908f9c949
This makes pytorch2.0 attention perform a bit faster.
2 years ago
comfyanonymous
907010e082
Remove some useless code.
2 years ago
comfyanonymous
96b57a9ad6
Don't pass adm to model when it doesn't support it.
2 years ago
comfyanonymous
3696d1699a
Add support for GLIGEN textbox model.
2 years ago
comfyanonymous
884ea653c8
Add a way for nodes to set a custom CFG function.
2 years ago
comfyanonymous
73c3e11e83
Fix model_management import so it doesn't get executed twice.
2 years ago
comfyanonymous
81d1f00df3
Some refactoring: from_tokens -> encode_from_tokens
2 years ago
BlenderNeko
d0b1b6c6bf
fixed improper padding
2 years ago
comfyanonymous
deb2b93e79
Move code to empty gpu cache to model_management.py
2 years ago
comfyanonymous
04d9bc13af
Safely load pickled embeds that don't load with weights_only=True.
2 years ago
BlenderNeko
da115bd78d
ensure backwards compat with optional args
2 years ago
BlenderNeko
752f7a162b
align behavior with old tokenize function
2 years ago
comfyanonymous
334aab05e5
Don't stop workflow if loading embedding fails.
2 years ago
BlenderNeko
73175cf58c
split tokenizer from encoder
2 years ago
BlenderNeko
8489cba140
add unique ID per word/embedding for tokenizer
2 years ago
comfyanonymous
92eca60ec9
Fix for new transformers version.
2 years ago
comfyanonymous
1e1875f674
Print xformers version and warning about 0.0.18
2 years ago
comfyanonymous
7e254d2f69
Clarify what --windows-standalone-build does.
2 years ago
comfyanonymous
44fea05064
Cleanup.
2 years ago
comfyanonymous
58ed0f2da4
Fix loading SD1.5 diffusers checkpoint.
2 years ago
comfyanonymous
64557d6781
Add a --force-fp32 argument to force fp32 for debugging.
2 years ago
comfyanonymous
bceccca0e5
Small refactor.
2 years ago
EllangoK
28fff5d1db
fixes lack of support for multi configs
...
also adds some metavars to argarse
2 years ago
comfyanonymous
f84f2508cc
Rename the cors parameter to something more verbose.
2 years ago
EllangoK
48efae1608
makes cors a cli parameter
2 years ago
EllangoK
01c1fc669f
set listen flag to listen on all if specifed
2 years ago
藍+85CD
3e2608e12b
Fix auto lowvram detection on CUDA
2 years ago
sALTaccount
60127a8304
diffusers loader
2 years ago
藍+85CD
7cb924f684
Use separate variables instead of `vram_state`
2 years ago
藍+85CD
84b9c0ac2f
Import intel_extension_for_pytorch as ipex
2 years ago
EllangoK
e5e587b1c0
seperates out arg parser and imports args
2 years ago
藍+85CD
37713e3b0a
Add basic XPU device support
...
closed #387
2 years ago
comfyanonymous
e46b1c3034
Disable xformers in VAE when xformers == 0.0.18
2 years ago
comfyanonymous
1718730e80
Ignore embeddings when sizes don't match and print a WARNING.
2 years ago
comfyanonymous
23524ad8c5
Remove print.
2 years ago
comfyanonymous
539ff487a8
Pull latest tomesd code from upstream.
2 years ago
comfyanonymous
f50b1fec69
Add noise augmentation setting to unCLIPConditioning.
2 years ago
comfyanonymous
809bcc8ceb
Add support for unCLIP SD2.x models.
...
See _for_testing/unclip in the UI for the new nodes.
unCLIPCheckpointLoader is used to load them.
unCLIPConditioning is used to add the image cond and takes as input a
CLIPVisionEncode output which has been moved to the conditioning section.
2 years ago