e1489ad257
Fix issue with lowvram mode breaking model saving.
6 months ago
93e876a3be
Remove warnings that confuse people.
6 months ago
c61eadf69a
Make the load checkpoint with config function call the regular one.
...
I was going to completely remove this function because it is unmaintainable
but I think this is the best compromise.
The clip skip and v_prediction parts of the configs should still work but
not the fp16 vs fp32.
6 months ago
8dc19e40d1
Don't init a VAE model when there are no VAE weights.
7 months ago
c59fe9f254
Support VAE without quant_conv.
7 months ago
30abc324c2
Support properly saving CosXL checkpoints.
7 months ago
0ed72befe1
Change log levels.
...
Logging level now defaults to info. --verbose sets it to debug.
8 months ago
65397ce601
Replace prints with logging and add --verbose argument.
8 months ago
ca7c310a0e
Support loading old CLIP models saved with CLIPSave.
9 months ago
c2cb8e889b
Always return unprojected pooled output for gligen.
9 months ago
1cb3f6a83b
Move text projection into the CLIP model code.
...
Fix issue with not loading the SSD1B clip correctly.
9 months ago
d91f45ef28
Some cleanups to how the text encoders are loaded.
9 months ago
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.
9 months ago
97d03ae04a
StableCascade CLIP model support.
9 months ago
f83109f09b
Stable Cascade Stage C.
9 months ago
5e06baf112
Stable Cascade Stage A.
9 months ago
38b7ac6e26
Don't init the CLIP model when the checkpoint has no CLIP weights.
9 months ago
da7a8df0d2
Put VAE key name in model config.
10 months ago
4871a36458
Cleanup some unused imports.
10 months ago
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.
10 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
5eddfdd80c
Refactor VAE code.
...
Replace constants with downscale_ratio and latent_channels.
11 months ago
824e4935f5
Add dtype parameter to VAE object.
11 months ago
ba07cb748e
Use faster manual cast for fp8 in unet.
11 months ago
9ac0b487ac
Make --gpu-only put intermediate values in GPU memory instead of cpu.
12 months ago
983ebc5792
Use smart model management for VAE to decrease latency.
12 months ago
c45d1b9b67
Add a function to load a unet from a state dict.
12 months ago
871cc20e13
Support SVD img2vid model.
12 months ago
410bf07771
Make VAE memory estimation take dtype into account.
1 year ago
6a491ebe27
Allow model config to preprocess the vae state dict on load.
1 year ago
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
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
0a6fd49a3e
Print leftover keys when using the UNETLoader.
1 year ago
2455aaed8a
Allow model or clip to be None in load_lora_for_models.
1 year ago
2a134bfab9
Fix checkpoint loader with config.
1 year ago
6ec3f12c6e
Support SSD1B model and make it easier to support asymmetric unets.
1 year ago
430a8334c5
Fix some potential issues.
1 year ago
d44a2de49f
Make VAE code closer to sgm.
1 year ago
9a55dadb4c
Refactor code so model can be a dtype other than fp32 or fp16.
1 year ago
72188dffc3
load_checkpoint_guess_config can now optionally output the model.
1 year ago
9bfec2bdbf
Fix quality loss due to low precision
1 year ago
71713888c4
Print missing VAE keys.
1 year ago
7d401ed1d0
Add ldm format support to UNETLoader.
1 year ago
7931ff0fd9
Support SDXL inpaint models.
1 year ago
fe4c07400c
Fix "Load Checkpoint with config" node.
1 year ago
1300a1bb4c
Text encoder should initially load on the offload_device not the regular.
1 year ago
f92074b84f
Move ModelPatcher to model_patcher.py
1 year ago
c77f02e1c6
Move controlnet code to comfy/controlnet.py
1 year ago
15a7716fa6
Move lora code to comfy/lora.py
1 year ago
ec96f6d03a
Move text_projection to base clip model.
1 year ago
comfyanonymous
City