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
51dde87e97
Try to free enough vram for control lora inference.
1 year ago
cc44ade79e
Always shift text encoder to GPU when the device supports fp16.
1 year ago
00c0b2c507
Initialize text encoder to target dtype.
1 year 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.
1 year ago
afcb9cb1df
All resolutions now work with t2i adapter for SDXL.
1 year ago
85fde89d7f
T2I adapter SDXL.
1 year ago
cf5ae46928
Controlnet/t2iadapter cleanup.
1 year ago
763b0cf024
Fix control lora not working in fp32.
1 year ago
199d73364a
Fix ControlLora on lowvram.
1 year ago
d08e53de2e
Remove autocast from controlnet code.
1 year ago
c9b562aed1
Free more memory before VAE encode/decode.
1 year 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.
1 year ago
c28db1f315
Fix potential issues with patching models when saving checkpoints.
1 year ago
89a0767abf
Smarter memory management.
...
Try to keep models on the vram when possible.
Better lowvram mode for controlnets.
1 year ago
53f326a3d8
Support diffusers mini controlnets.
1 year ago
c8a23ce9e8
Support for yet another lora type based on diffusers.
1 year ago
c20583286f
Support diffuser text encoder loras.
1 year ago
d8e58f0a7e
Detect hint_channels from controlnet.
1 year ago
c5d7593ccf
Support loras in diffusers format.
1 year ago
4b957a0010
Initialize the unet directly on the target device.
1 year ago
727588d076
Fix some new loras.
1 year ago
5f75d784a1
Start is now 0.0 and end is now 1.0 for the timestep ranges.
1 year ago
7ff14b62f8
ControlNetApplyAdvanced can now define when controlnet gets applied.
1 year ago
22f29d66ca
Try to fix memory issue with lora.
1 year ago
12a6e93171
Del the right object when applying lora.
1 year ago
78e7958d17
Support controlnet in diffusers format.
1 year ago
09386a3697
Fix issue with lora in some cases when combined with model merging.
1 year ago
58b2364f58
Properly support SDXL diffusers unet with UNETLoader node.
1 year ago
0115018695
Print errors and continue when lora weights are not compatible.
1 year ago
3ded1a3a04
Refactor of sampler code to deal more easily with different model types.
1 year ago
5f57362613
Lower lora ram usage when in normal vram mode.
1 year ago
490771b7f4
Speed up lora loading a bit.
1 year ago
50b1180dde
Fix CLIPSetLastLayer not reverting when removed.
1 year ago
6fb084f39d
Reduce floating point rounding errors in loras.
1 year ago
91ed2815d5
Add a node to merge CLIP models.
1 year ago
6ad0a6d7e2
Don't patch weights when multiplier is zero.
1 year ago
a9a4ba7574
Fix merging not working when model2 of model merge node was a merge.
1 year ago
e7bee85df8
Add arguments to run the VAE in fp16 or bf16 for testing.
1 year ago
ddc6f12ad5
Disable autocast in unet for increased speed.
1 year ago
af7a49916b
Support loading unet files in diffusers format.
1 year ago
acf95191ff
Properly support SDXL diffusers loras for unet.
1 year ago
c3e96e637d
Pass device to CLIP model.
1 year ago
2c4e0b49b7
Switch to fp16 on some cards when the model is too big.
1 year ago
1c1b0e7299
--gpu-only now keeps the VAE on the device.
1 year ago
3b6fe51c1d
Leave text_encoder on the CPU when it can handle it.
1 year ago
comfyanonymous