bb4940d837
Only enable attention upcasting on models that actually need it.
6 months ago
1088d1850f
Support for CosXL models.
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
327ca1313d
Support SDXS 0.9
8 months ago
40e124c6be
SV3D support.
8 months ago
cacb022c4a
Make saved SD1 checkpoints match more closely the official one.
8 months ago
b3e97fc714
Koala 700M and 1B support.
...
Use the UNET Loader node to load the unet file to use them.
9 months ago
8daedc5bf2
Auto detect playground v2.5 model.
9 months ago
1e0fcc9a65
Make XL checkpoints save in a more standard format.
9 months ago
1cb3f6a83b
Move text projection into the CLIP model code.
...
Fix issue with not loading the SSD1B clip correctly.
9 months ago
3711b31dff
Support Stable Cascade in checkpoint format.
9 months ago
d91f45ef28
Some cleanups to how the text encoders are loaded.
9 months ago
5b40e7a5ed
Implement shift schedule for cascade stage C.
9 months ago
97d03ae04a
StableCascade CLIP model support.
9 months ago
667c92814e
Stable Cascade Stage B.
9 months ago
f83109f09b
Stable Cascade Stage C.
9 months ago
8c6493578b
Implement noise augmentation for SD 4X upscale model.
11 months ago
a7874d1a8b
Add support for the stable diffusion x4 upscaling model.
...
This is an old model.
Load the checkpoint like a regular one and use the new
SD_4XUpscale_Conditioning node.
11 months ago
2258f85159
Support stable zero 123 model.
...
To use it use the ImageOnlyCheckpointLoader to load the checkpoint and
the new Stable_Zero123 node.
11 months ago
b454a67bb9
Support segmind vega model.
11 months ago
c97be4db91
Support SD2.1 turbo checkpoint.
12 months ago
871cc20e13
Support SVD img2vid model.
12 months ago
e60ca6929a
SD1 and SD2 clip and tokenizer code is now more similar to the SDXL one.
1 year ago
6ec3f12c6e
Support SSD1B model and make it easier to support asymmetric unets.
1 year ago
a74c5dbf37
Move some functions to utils.py
1 year ago
7931ff0fd9
Support SDXL inpaint models.
1 year ago
4b957a0010
Initialize the unet directly on the target device.
1 year ago
4f9b6f39d1
Fix potential issue with Save Checkpoint.
1 year ago
3ded1a3a04
Refactor of sampler code to deal more easily with different model types.
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
af7a49916b
Support loading unet files in diffusers format.
1 year ago
f81b192944
Add logit scale parameter so it's present when saving the checkpoint.
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
8607c2d42d
Move latent scale factor from VAE to model.
1 year ago
f87ec10a97
Support base SDXL and SDXL refiner models.
...
Large refactor of the model detection and loading code.
1 year ago
comfyanonymous