comfyanonymous
be891646cd
Allow passing custom path to clip-g and clip-h.
2023-07-03 15:45:04 -04:00
comfyanonymous
fd93e324e8
Improvements for OSX.
2023-07-03 00:08:30 -04:00
comfyanonymous
033dc1f52a
Cleanup.
2023-07-02 11:58:23 -04:00
comfyanonymous
280a4e3544
Switch to fp16 on some cards when the model is too big.
2023-07-02 10:00:57 -04:00
comfyanonymous
dd4abf1345
Add a --force-fp16 argument to force fp16 for testing.
2023-07-01 22:42:35 -04:00
comfyanonymous
1e24a78d85
--gpu-only now keeps the VAE on the device.
2023-07-01 15:22:40 -04:00
comfyanonymous
5ace1146c5
Lower latency by batching some text encoder inputs.
2023-07-01 15:07:39 -04:00
comfyanonymous
2ee0aa317c
Leave text_encoder on the CPU when it can handle it.
2023-07-01 14:38:51 -04:00
comfyanonymous
d5a7abe10d
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
comfyanonymous
e946dca0e1
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
comfyanonymous
7dff6c094c
LoraLoader node now caches the lora file between executions.
2023-06-29 23:40:51 -04:00
comfyanonymous
7520fc3eac
Fix embeddings not working with --gpu-only
2023-06-29 20:43:06 -04:00
comfyanonymous
790073a21d
Move unet to device right after loading on highvram mode.
2023-06-29 20:43:06 -04:00
comfyanonymous
a9b4d721c0
Remove useless code.
2023-06-29 00:26:33 -04:00
comfyanonymous
edfb14822e
This is unused but it should be 1280.
2023-06-28 18:04:23 -04:00
comfyanonymous
ae27a5625e
Support for SDXL text encoder lora.
2023-06-28 02:22:49 -04:00
comfyanonymous
73519d4e76
Fix bug.
2023-06-28 00:38:07 -04:00
comfyanonymous
7b13cacfea
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
comfyanonymous
95008c22cd
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
comfyanonymous
0254a9d75b
Support loras based on the stability unet implementation.
2023-06-26 02:56:11 -04:00
comfyanonymous
44e3d3caed
Fix ddim + inpainting not working.
2023-06-26 00:48:48 -04:00
comfyanonymous
a098d7e4d2
Set the seed in the SDE samplers to make them more reproducible.
2023-06-25 03:04:57 -04:00
comfyanonymous
6d80c5ed30
Add support for TAESD decoder for SDXL.
2023-06-25 02:38:14 -04:00
comfyanonymous
c4c2db6ead
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
comfyanonymous
818bae8e52
Fix CLIPLoader node.
2023-06-24 13:56:46 -04:00
comfyanonymous
391ee8d21f
Fix bug with controlnet.
2023-06-24 11:02:38 -04:00
comfyanonymous
0db33017af
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
comfyanonymous
51da619d73
Remove useless code.
2023-06-23 12:35:26 -04:00
comfyanonymous
a852d8b138
Move latent scale factor from VAE to model.
2023-06-23 02:33:31 -04:00
comfyanonymous
288f0c430d
Fix bug when yaml config has no clip params.
2023-06-23 01:12:59 -04:00
comfyanonymous
40f218c4fa
Fix error with ClipVision loader node.
2023-06-23 01:08:05 -04:00
comfyanonymous
4ed8aea1a1
Don't merge weights when shapes don't match and print a warning.
2023-06-22 19:08:31 -04:00
comfyanonymous
08f1f7686c
Support base SDXL and SDXL refiner models.
...
Large refactor of the model detection and loading code.
2023-06-22 13:03:50 -04:00
comfyanonymous
d72d5d49f5
Add original_shape parameter to transformer patch extra_options.
2023-06-21 13:22:01 -04:00
comfyanonymous
cd8d0b73c5
Fix last commits causing an issue with the text encoder lora.
2023-06-20 19:44:39 -04:00
comfyanonymous
af9e05f389
Keep a set of model_keys for faster add_patches.
2023-06-20 19:08:48 -04:00
comfyanonymous
2c71c47ff9
Add a type of model patch useful for model merging.
2023-06-20 17:34:11 -04:00
comfyanonymous
5384849e5e
Fix k_diffusion math being off by a tiny bit during txt2img.
2023-06-19 15:28:54 -04:00
comfyanonymous
873b08bd0f
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
comfyanonymous
26bce56c3b
pop clip vision keys after loading them.
2023-06-18 21:21:17 -04:00
comfyanonymous
c1e1b00941
Not needed anymore.
2023-06-18 13:06:59 -04:00
comfyanonymous
78eabd0fd4
This is not needed anymore and causes issues with alphas_cumprod.
2023-06-18 03:18:25 -04:00
comfyanonymous
351d778487
Fix DDIM v-prediction.
2023-06-17 20:48:21 -04:00
comfyanonymous
a93a785f9e
Fix an issue when alphas_comprod are half floats.
2023-06-16 17:16:51 -04:00
comfyanonymous
d35c0ce6ec
All the unet weights should now be initialized with the right dtype.
2023-06-15 18:42:30 -04:00
comfyanonymous
282638b813
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
comfyanonymous
8e6cbe6270
Initialize more unet weights as the right dtype.
2023-06-15 15:00:10 -04:00
comfyanonymous
206af9a315
Initialize transformer unet block weights in right dtype at the start.
2023-06-15 14:29:26 -04:00
comfyanonymous
16c535a309
Properly disable weight initialization in clip models.
2023-06-14 20:13:08 -04:00
comfyanonymous
6bbd86a061
Disable default weight values in unet conv2d for faster loading.
2023-06-14 19:46:08 -04:00
