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
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
comfyanonymous
City