comfyanonymous
|
0ed72befe1
|
Change log levels.
Logging level now defaults to info. --verbose sets it to debug.
|
12 months ago |
|
comfyanonymous
|
65397ce601
|
Replace prints with logging and add --verbose argument.
|
12 months ago |
|
comfyanonymous
|
ca7c310a0e
|
Support loading old CLIP models saved with CLIPSave.
|
1 year ago |
|
comfyanonymous
|
c2cb8e889b
|
Always return unprojected pooled output for gligen.
|
1 year ago |
|
comfyanonymous
|
1cb3f6a83b
|
Move text projection into the CLIP model code.
Fix issue with not loading the SSD1B clip correctly.
|
1 year ago |
|
comfyanonymous
|
d91f45ef28
|
Some cleanups to how the text encoders are loaded.
|
1 year ago |
|
comfyanonymous
|
3b2e579926
|
Support loading the Stable Cascade effnet and previewer as a VAE.
The effnet can be used to encode images for img2img with Stage C.
|
1 year ago |
|
comfyanonymous
|
97d03ae04a
|
StableCascade CLIP model support.
|
1 year ago |
|
comfyanonymous
|
f83109f09b
|
Stable Cascade Stage C.
|
1 year ago |
|
comfyanonymous
|
5e06baf112
|
Stable Cascade Stage A.
|
1 year ago |
|
comfyanonymous
|
38b7ac6e26
|
Don't init the CLIP model when the checkpoint has no CLIP weights.
|
1 year ago |
|
comfyanonymous
|
da7a8df0d2
|
Put VAE key name in model config.
|
1 year ago |
|
comfyanonymous
|
4871a36458
|
Cleanup some unused imports.
|
1 year ago |
|
comfyanonymous
|
d76a04b6ea
|
Add unfinished ImageOnlyCheckpointSave node to save a SVD checkpoint.
This node is unfinished, SVD checkpoints saved with this node will
work with ComfyUI but not with anything else.
|
1 year ago |
|
comfyanonymous
|
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.
|
1 year ago |
|
comfyanonymous
|
5eddfdd80c
|
Refactor VAE code.
Replace constants with downscale_ratio and latent_channels.
|
1 year ago |
|
comfyanonymous
|
824e4935f5
|
Add dtype parameter to VAE object.
|
1 year ago |
|
comfyanonymous
|
ba07cb748e
|
Use faster manual cast for fp8 in unet.
|
1 year ago |
|
comfyanonymous
|
9ac0b487ac
|
Make --gpu-only put intermediate values in GPU memory instead of cpu.
|
1 year ago |
|
comfyanonymous
|
983ebc5792
|
Use smart model management for VAE to decrease latency.
|
1 year ago |
|
comfyanonymous
|
c45d1b9b67
|
Add a function to load a unet from a state dict.
|
1 year ago |
|
comfyanonymous
|
871cc20e13
|
Support SVD img2vid model.
|
1 year ago |
|
comfyanonymous
|
410bf07771
|
Make VAE memory estimation take dtype into account.
|
1 year ago |
|
comfyanonymous
|
6a491ebe27
|
Allow model config to preprocess the vae state dict on load.
|
1 year ago |
|
comfyanonymous
|
cd4fc77d5f
|
Add taesd and taesdxl to VAELoader node.
They will show up if both the taesd_encoder and taesd_decoder or taesdxl
model files are present in the models/vae_approx directory.
|
1 year ago |
|
comfyanonymous
|
0cf4e86939
|
Add some command line arguments to store text encoder weights in fp8.
Pytorch supports two variants of fp8:
--fp8_e4m3fn-text-enc (the one that seems to give better results)
--fp8_e5m2-text-enc
|
1 year ago |
|
comfyanonymous
|
0a6fd49a3e
|
Print leftover keys when using the UNETLoader.
|
1 year ago |
|
comfyanonymous
|
2455aaed8a
|
Allow model or clip to be None in load_lora_for_models.
|
1 year ago |
|
comfyanonymous
|
2a134bfab9
|
Fix checkpoint loader with config.
|
1 year ago |
|
comfyanonymous
|
6ec3f12c6e
|
Support SSD1B model and make it easier to support asymmetric unets.
|
1 year ago |
|
comfyanonymous
|
430a8334c5
|
Fix some potential issues.
|
1 year ago |
|
comfyanonymous
|
d44a2de49f
|
Make VAE code closer to sgm.
|
1 year ago |
|
comfyanonymous
|
9a55dadb4c
|
Refactor code so model can be a dtype other than fp32 or fp16.
|
1 year ago |
|
comfyanonymous
|
72188dffc3
|
load_checkpoint_guess_config can now optionally output the model.
|
1 year ago |
City
|
9bfec2bdbf
|
Fix quality loss due to low precision
|
1 year ago |
|
comfyanonymous
|
71713888c4
|
Print missing VAE keys.
|
1 year ago |
|
comfyanonymous
|
7d401ed1d0
|
Add ldm format support to UNETLoader.
|
1 year ago |
|
comfyanonymous
|
7931ff0fd9
|
Support SDXL inpaint models.
|
2 years ago |
|
comfyanonymous
|
fe4c07400c
|
Fix "Load Checkpoint with config" node.
|
2 years ago |
|
comfyanonymous
|
1300a1bb4c
|
Text encoder should initially load on the offload_device not the regular.
|
2 years ago |
|
comfyanonymous
|
f92074b84f
|
Move ModelPatcher to model_patcher.py
|
2 years ago |
|
comfyanonymous
|
c77f02e1c6
|
Move controlnet code to comfy/controlnet.py
|
2 years ago |
|
comfyanonymous
|
15a7716fa6
|
Move lora code to comfy/lora.py
|
2 years ago |
|
comfyanonymous
|
ec96f6d03a
|
Move text_projection to base clip model.
|
2 years ago |
|
comfyanonymous
|
51dde87e97
|
Try to free enough vram for control lora inference.
|
2 years ago |
|
comfyanonymous
|
cc44ade79e
|
Always shift text encoder to GPU when the device supports fp16.
|
2 years ago |
|
comfyanonymous
|
00c0b2c507
|
Initialize text encoder to target dtype.
|
2 years ago |
|
comfyanonymous
|
f081017c1a
|
Save memory by storing text encoder weights in fp16 in most situations.
Do inference in fp32 to make sure quality stays the exact same.
|
2 years ago |
|
comfyanonymous
|
afcb9cb1df
|
All resolutions now work with t2i adapter for SDXL.
|
2 years ago |
|
comfyanonymous
|
85fde89d7f
|
T2I adapter SDXL.
|
2 years ago |