1679abd86d
Add a command line argument to enable backend:cudaMallocAsync
1 year ago
3a150bad15
Only calculate randn in some samplers when it's actually being used.
1 year ago
ee8f8ee07f
Fix regression with ddim and uni_pc when batch size > 1.
1 year ago
3ded1a3a04
Refactor of sampler code to deal more easily with different model types.
1 year ago
5f57362613
Lower lora ram usage when in normal vram mode.
1 year ago
490771b7f4
Speed up lora loading a bit.
1 year ago
50b1180dde
Fix CLIPSetLastLayer not reverting when removed.
1 year ago
6fb084f39d
Reduce floating point rounding errors in loras.
1 year ago
91ed2815d5
Add a node to merge CLIP models.
1 year ago
b2f03164c7
Prevent the clip_g position_ids key from being saved in the checkpoint.
...
This is to make it match the official checkpoint.
1 year ago
46dc050c9f
Fix potential tensors being on different devices issues.
1 year ago
3e2309f149
fix mps miss import
1 year ago
606a537090
Support SDXL embedding format with 2 CLIP.
1 year ago
6ad0a6d7e2
Don't patch weights when multiplier is zero.
1 year ago
d5323d16e0
latent2rgb matrix for SDXL.
1 year ago
0ae81c03bb
Empty cache after model unloading for normal vram and lower.
1 year ago
d3f5998218
Support loading clip_g from diffusers in CLIP Loader nodes.
1 year ago
a9a4ba7574
Fix merging not working when model2 of model merge node was a merge.
1 year ago
e7bee85df8
Add arguments to run the VAE in fp16 or bf16 for testing.
1 year ago
608fcc2591
Fix bug with weights when prompt is long.
1 year ago
ddc6f12ad5
Disable autocast in unet for increased speed.
1 year ago
603f02d613
Fix loras not working when loading checkpoint with config.
1 year ago
af7a49916b
Support loading unet files in diffusers format.
1 year ago
e57cba4c61
Add gpu variations of the sde samplers that are less deterministic
...
but faster.
1 year ago
f81b192944
Add logit scale parameter so it's present when saving the checkpoint.
1 year ago
acf95191ff
Properly support SDXL diffusers loras for unet.
1 year ago
c61a95f9f7
Fix size check for conditioning mask
...
The wrong dimensions were being checked, [1] and [2] are the image size.
not [2] and [3]. This results in an out-of-bounds error if one of them
actually matches.
1 year ago
8d694cc450
Fix issue with OSX.
1 year ago
c3e96e637d
Pass device to CLIP model.
1 year ago
5e6bc824aa
Allow passing custom path to clip-g and clip-h.
1 year ago
dc9d1f31c8
Improvements for OSX.
1 year ago
103c487a89
Cleanup.
1 year ago
2c4e0b49b7
Switch to fp16 on some cards when the model is too big.
1 year ago
6f3d9f52db
Add a --force-fp16 argument to force fp16 for testing.
1 year ago
1c1b0e7299
--gpu-only now keeps the VAE on the device.
1 year ago
ce35d8c659
Lower latency by batching some text encoder inputs.
1 year ago
3b6fe51c1d
Leave text_encoder on the CPU when it can handle it.
1 year ago
b6a60fa696
Try to keep text encoders loaded and patched to increase speed.
...
load_model_gpu() is now used with the text encoder models instead of just
the unet.
1 year ago
97ee230682
Make highvram and normalvram shift the text encoders to vram and back.
...
This is faster on big text encoder models than running it on the CPU.
1 year ago
5a9ddf94eb
LoraLoader node now caches the lora file between executions.
1 year ago
9920367d3c
Fix embeddings not working with --gpu-only
1 year ago
62db11683b
Move unet to device right after loading on highvram mode.
1 year ago
4376b125eb
Remove useless code.
1 year ago
89120f1fbe
This is unused but it should be 1280.
1 year ago
2c7c14de56
Support for SDXL text encoder lora.
1 year ago
fcef47f06e
Fix bug.
1 year ago
8248babd44
Use pytorch attention by default on nvidia when xformers isn't present.
...
Add a new argument --use-quad-cross-attention
1 year ago
9b93b920be
Add CheckpointSave node to save checkpoints.
...
The created checkpoints contain workflow metadata that can be loaded by
dragging them on top of the UI or loading them with the "Load" button.
Checkpoints will be saved in fp16 or fp32 depending on the format ComfyUI
is using for inference on your hardware. To force fp32 use: --force-fp32
Anything that patches the model weights like merging or loras will be
saved.
The output directory is currently set to: output/checkpoints but that might
change in the future.
1 year ago
b72a7a835a
Support loras based on the stability unet implementation.
1 year ago
c71a7e6b20
Fix ddim + inpainting not working.
1 year ago
comfyanonymous
KarryCharon
mara