2c4e0b49b7
Switch to fp16 on some cards when the model is too big.
2023-07-02 10:00:57 -04:00
6f3d9f52db
Add a --force-fp16 argument to force fp16 for testing.
2023-07-01 22:42:35 -04:00
1c1b0e7299
--gpu-only now keeps the VAE on the device.
2023-07-01 15:22:40 -04:00
ce35d8c659
Lower latency by batching some text encoder inputs.
2023-07-01 15:07:39 -04:00
3b6fe51c1d
Leave text_encoder on the CPU when it can handle it.
2023-07-01 14:38:51 -04:00
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.
2023-07-01 13:28:07 -04:00
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.
2023-07-01 12:37:23 -04:00
5a9ddf94eb
LoraLoader node now caches the lora file between executions.
2023-06-29 23:40:51 -04:00
9920367d3c
Fix embeddings not working with --gpu-only
2023-06-29 20:43:06 -04:00
62db11683b
Move unet to device right after loading on highvram mode.
2023-06-29 20:43:06 -04:00
4376b125eb
Remove useless code.
2023-06-29 00:26:33 -04:00
89120f1fbe
This is unused but it should be 1280.
2023-06-28 18:04:23 -04:00
2c7c14de56
Support for SDXL text encoder lora.
2023-06-28 02:22:49 -04:00
fcef47f06e
Fix bug.
2023-06-28 00:38:07 -04:00
8248babd44
Use pytorch attention by default on nvidia when xformers isn't present.
...
Add a new argument --use-quad-cross-attention
2023-06-26 13:03:44 -04:00
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.
2023-06-26 12:22:27 -04:00
b72a7a835a
Support loras based on the stability unet implementation.
2023-06-26 02:56:11 -04:00
c71a7e6b20
Fix ddim + inpainting not working.
2023-06-26 00:48:48 -04:00
4eab00e14b
Set the seed in the SDE samplers to make them more reproducible.
2023-06-25 03:04:57 -04:00
cef6aa62b2
Add support for TAESD decoder for SDXL.
2023-06-25 02:38:14 -04:00
20f579d91d
Add DualClipLoader to load clip models for SDXL.
...
Update LoadClip to load clip models for SDXL refiner.
2023-06-25 01:40:38 -04:00
b7933960bb
Fix CLIPLoader node.
2023-06-24 13:56:46 -04:00
78d8035f73
Fix bug with controlnet.
2023-06-24 11:02:38 -04:00
05676942b7
Add some more transformer hooks and move tomesd to comfy_extras.
...
Tomesd now uses q instead of x to decide which tokens to merge because
it seems to give better results.
2023-06-24 03:30:22 -04:00
fa28d7334b
Remove useless code.
2023-06-23 12:35:26 -04:00
8607c2d42d
Move latent scale factor from VAE to model.
2023-06-23 02:33:31 -04:00
30a3861946
Fix bug when yaml config has no clip params.
2023-06-23 01:12:59 -04:00
9e37f4c7d5
Fix error with ClipVision loader node.
2023-06-23 01:08:05 -04:00
9f83b098c9
Don't merge weights when shapes don't match and print a warning.
2023-06-22 19:08:31 -04:00
f87ec10a97
Support base SDXL and SDXL refiner models.
...
Large refactor of the model detection and loading code.
2023-06-22 13:03:50 -04:00
9fccf4aa03
Add original_shape parameter to transformer patch extra_options.
2023-06-21 13:22:01 -04:00
51581dbfa9
Fix last commits causing an issue with the text encoder lora.
2023-06-20 19:44:39 -04:00
8125b51a62
Keep a set of model_keys for faster add_patches.
2023-06-20 19:08:48 -04:00
45beebd33c
Add a type of model patch useful for model merging.
2023-06-20 17:34:11 -04:00
036a22077c
Fix k_diffusion math being off by a tiny bit during txt2img.
2023-06-19 15:28:54 -04:00
8883cb0f67
Add a way to set patches that modify the attn2 output.
...
Change the transformer patches function format to be more future proof.
2023-06-18 22:58:22 -04:00
cd930d4e7f
pop clip vision keys after loading them.
2023-06-18 21:21:17 -04:00
c9e4a8c9e5
Not needed anymore.
2023-06-18 13:06:59 -04:00
fb4bf7f591
This is not needed anymore and causes issues with alphas_cumprod.
2023-06-18 03:18:25 -04:00
45be2e92c1
Fix DDIM v-prediction.
2023-06-17 20:48:21 -04:00
e6e50ab2dd
Fix an issue when alphas_comprod are half floats.
2023-06-16 17:16:51 -04:00
ae43f09ef7
All the unet weights should now be initialized with the right dtype.
2023-06-15 18:42:30 -04:00
f7edcfd927
Add a --gpu-only argument to keep and run everything on the GPU.
...
Make the CLIP model work on the GPU.
2023-06-15 15:38:52 -04:00
7bf89ba923
Initialize more unet weights as the right dtype.
2023-06-15 15:00:10 -04:00
e21d9ad445
Initialize transformer unet block weights in right dtype at the start.
2023-06-15 14:29:26 -04:00
bb1f45d6e8
Properly disable weight initialization in clip models.
2023-06-14 20:13:08 -04:00
21f04fe632
Disable default weight values in unet conv2d for faster loading.
2023-06-14 19:46:08 -04:00
9d54066ebc
This isn't needed for inference.
2023-06-14 13:05:08 -04:00
fa2cca056c
Don't initialize CLIPVision weights to default values.
2023-06-14 12:57:02 -04:00
6b774589a5
Set model to fp16 before loading the state dict to lower ram bump.
2023-06-14 12:48:02 -04:00
