c59fe9f254
Support VAE without quant_conv.
10 months ago
30abc324c2
Support properly saving CosXL checkpoints.
11 months ago
0ed72befe1
Change log levels.
...
Logging level now defaults to info. --verbose sets it to debug.
12 months ago
65397ce601
Replace prints with logging and add --verbose argument.
12 months ago
ca7c310a0e
Support loading old CLIP models saved with CLIPSave.
1 year ago
c2cb8e889b
Always return unprojected pooled output for gligen.
1 year ago
1cb3f6a83b
Move text projection into the CLIP model code.
...
Fix issue with not loading the SSD1B clip correctly.
1 year ago
d91f45ef28
Some cleanups to how the text encoders are loaded.
1 year 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.
1 year ago
97d03ae04a
StableCascade CLIP model support.
1 year ago
f83109f09b
Stable Cascade Stage C.
1 year ago
5e06baf112
Stable Cascade Stage A.
1 year ago
38b7ac6e26
Don't init the CLIP model when the checkpoint has no CLIP weights.
1 year ago
da7a8df0d2
Put VAE key name in model config.
1 year ago
4871a36458
Cleanup some unused imports.
1 year 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.
1 year 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.
1 year ago
5eddfdd80c
Refactor VAE code.
...
Replace constants with downscale_ratio and latent_channels.
1 year ago
824e4935f5
Add dtype parameter to VAE object.
1 year ago
ba07cb748e
Use faster manual cast for fp8 in unet.
1 year ago
9ac0b487ac
Make --gpu-only put intermediate values in GPU memory instead of cpu.
1 year ago
983ebc5792
Use smart model management for VAE to decrease latency.
1 year ago
c45d1b9b67
Add a function to load a unet from a state dict.
1 year ago
871cc20e13
Support SVD img2vid model.
1 year 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.
2 years ago
fe4c07400c
Fix "Load Checkpoint with config" node.
2 years ago
1300a1bb4c
Text encoder should initially load on the offload_device not the regular.
2 years ago
f92074b84f
Move ModelPatcher to model_patcher.py
2 years ago
c77f02e1c6
Move controlnet code to comfy/controlnet.py
2 years ago
15a7716fa6
Move lora code to comfy/lora.py
2 years ago
ec96f6d03a
Move text_projection to base clip model.
2 years ago
51dde87e97
Try to free enough vram for control lora inference.
2 years ago
cc44ade79e
Always shift text encoder to GPU when the device supports fp16.
2 years ago
00c0b2c507
Initialize text encoder to target dtype.
2 years ago
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
afcb9cb1df
All resolutions now work with t2i adapter for SDXL.
2 years ago
85fde89d7f
T2I adapter SDXL.
2 years ago
cf5ae46928
Controlnet/t2iadapter cleanup.
2 years ago
763b0cf024
Fix control lora not working in fp32.
2 years ago
199d73364a
Fix ControlLora on lowvram.
2 years ago
d08e53de2e
Remove autocast from controlnet code.
2 years ago
c9b562aed1
Free more memory before VAE encode/decode.
2 years ago
d6e4b342e6
Support for Control Loras.
...
Control loras are controlnets where some of the weights are stored in
"lora" format: an up and a down low rank matrice that when multiplied
together and added to the unet weight give the controlnet weight.
This allows a much smaller memory footprint depending on the rank of the
matrices.
These controlnets are used just like regular ones.
2 years ago
c28db1f315
Fix potential issues with patching models when saving checkpoints.
2 years ago
89a0767abf
Smarter memory management.
...
Try to keep models on the vram when possible.
Better lowvram mode for controlnets.
2 years ago
53f326a3d8
Support diffusers mini controlnets.
2 years ago
c8a23ce9e8
Support for yet another lora type based on diffusers.
2 years ago
c20583286f
Support diffuser text encoder loras.
2 years ago
d8e58f0a7e
Detect hint_channels from controlnet.
2 years ago
c5d7593ccf
Support loras in diffusers format.
2 years ago
4b957a0010
Initialize the unet directly on the target device.
2 years ago
727588d076
Fix some new loras.
2 years ago
5f75d784a1
Start is now 0.0 and end is now 1.0 for the timestep ranges.
2 years ago
7ff14b62f8
ControlNetApplyAdvanced can now define when controlnet gets applied.
2 years ago
22f29d66ca
Try to fix memory issue with lora.
2 years ago
12a6e93171
Del the right object when applying lora.
2 years ago
78e7958d17
Support controlnet in diffusers format.
2 years ago
09386a3697
Fix issue with lora in some cases when combined with model merging.
2 years ago
58b2364f58
Properly support SDXL diffusers unet with UNETLoader node.
2 years ago
0115018695
Print errors and continue when lora weights are not compatible.
2 years ago
3ded1a3a04
Refactor of sampler code to deal more easily with different model types.
2 years ago
5f57362613
Lower lora ram usage when in normal vram mode.
2 years ago
490771b7f4
Speed up lora loading a bit.
2 years ago
50b1180dde
Fix CLIPSetLastLayer not reverting when removed.
2 years ago
6fb084f39d
Reduce floating point rounding errors in loras.
2 years ago
91ed2815d5
Add a node to merge CLIP models.
2 years ago
6ad0a6d7e2
Don't patch weights when multiplier is zero.
2 years ago
a9a4ba7574
Fix merging not working when model2 of model merge node was a merge.
2 years ago
e7bee85df8
Add arguments to run the VAE in fp16 or bf16 for testing.
2 years ago
ddc6f12ad5
Disable autocast in unet for increased speed.
2 years ago
af7a49916b
Support loading unet files in diffusers format.
2 years ago
acf95191ff
Properly support SDXL diffusers loras for unet.
2 years ago
c3e96e637d
Pass device to CLIP model.
2 years ago
2c4e0b49b7
Switch to fp16 on some cards when the model is too big.
2 years ago
1c1b0e7299
--gpu-only now keeps the VAE on the device.
2 years ago
3b6fe51c1d
Leave text_encoder on the CPU when it can handle it.
2 years ago
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.
2 years ago
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.
2 years ago
5a9ddf94eb
LoraLoader node now caches the lora file between executions.
2 years ago
62db11683b
Move unet to device right after loading on highvram mode.
2 years ago
2c7c14de56
Support for SDXL text encoder lora.
2 years 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.
2 years ago
b72a7a835a
Support loras based on the stability unet implementation.
2 years ago
20f579d91d
Add DualClipLoader to load clip models for SDXL.
...
Update LoadClip to load clip models for SDXL refiner.
2 years ago
b7933960bb
Fix CLIPLoader node.
2 years ago
comfyanonymous
City