d1a6bd6845
Support loading long clipl model with the CLIP loader node.
6 months ago
9eee470244
New load_text_encoder_state_dicts function.
...
Now you can load text encoders straight from a list of state dicts.
6 months ago
4f7a3cb6fb
unet -> diffusion_models.
6 months ago
fca42836f2
Add model_options for text encoder.
6 months ago
74e124f4d7
Fix some issues with TE being in lowvram mode.
6 months ago
a562c17e8a
load_unet -> load_diffusion_model with a model_options argument.
6 months ago
ad76574cb8
Fix some potential issues with the previous commits.
6 months ago
9acfe4df41
Support loading directly to vram with CLIPLoader node.
6 months ago
9829b013ea
Fix mistake in last commit.
6 months ago
5c69cde037
Load TE model straight to vram if certain conditions are met.
6 months ago
e9589d6d92
Add a way to set model dtype and ops from load_checkpoint_guess_config.
7 months ago
0d82a798a5
Remove the ckpt_path from load_state_dict_guess_config.
7 months ago
925fff26fd
alternative to `load_checkpoint_guess_config` that accepts a loaded state dict ( #4249 )
...
* make alternative fn
* add back ckpt path as 2nd argument?
7 months ago
b334605a66
Fix OOMs happening in some cases.
...
A cloned model patcher sometimes reported a model was loaded on a device
when it wasn't.
7 months ago
2ba5cc8b86
Fix some issues.
7 months ago
ba9095e5bd
Automatically use fp8 for diffusion model weights if:
...
Checkpoint contains weights in fp8.
There isn't enough memory to load the diffusion model in GPU vram.
7 months ago
d7430a1651
Add a way to load the diffusion model in fp8 with UNETLoader node.
7 months ago
5f98de7697
Load flux t5 in fp8 if weights are in fp8.
7 months ago
1589b58d3e
Basic Flux Schnell and Flux Dev model implementation.
7 months ago
4ba7fa0244
Refactor: Move sd2_clip.py to text_encoders folder.
7 months ago
a5f4292f9f
Basic hunyuan dit implementation. ( #4102 )
...
* Let tokenizers return weights to be stored in the saved checkpoint.
* Basic hunyuan dit implementation.
* Fix some resolutions not working.
* Support hydit checkpoint save.
* Init with right dtype.
* Switch to optimized attention in pooler.
* Fix black images on hunyuan dit.
7 months ago
f87810cd3e
Let tokenizers return weights to be stored in the saved checkpoint.
7 months ago
10c919f4c7
Make it possible to load tokenizer data from checkpoints.
7 months ago
1305fb294c
Refactor: Move some code to the comfy/text_encoders folder.
7 months ago
a3dffc447a
Support AuraFlow Lora and loading model weights in diffusers format.
...
You can load model weights in diffusers format using the UNETLoader node.
7 months ago
9f291d75b3
AuraFlow model implementation.
8 months ago
f45157e3ac
Fix error message never being shown.
8 months ago
5e1fced639
Cleaner support for loading different diffusion model types.
8 months ago
ffe0bb0a33
Remove useless code.
8 months ago
391c1046cf
More flexibility with text encoder return values.
...
Text encoders can now return other values to the CONDITIONING than the cond
and pooled output.
8 months ago
4040491149
Better T5xxl detection.
8 months ago
d7484ef30c
Support loading checkpoints with the UNETLoader node.
8 months ago
537f35c7bc
Don't update dict if contiguous.
8 months ago
3f46362d22
fix non-contiguous tensor saving (from channels-last) ( #3932 )
8 months ago
8ceb5a02a3
Support saving stable audio checkpoint that can be loaded back.
8 months ago
4ef1479dcd
Multi dimension tiled scale function and tiled VAE audio encoding fallback.
8 months ago
1e2839f4d9
More proper tiled audio decoding.
8 months ago
0d6a57938e
Support loading diffusers SD3 model format with UNETLoader node.
8 months ago
a45df69570
Basic tiled decoding for audio VAE.
8 months ago
6425252c4f
Use fp16 as the default vae dtype for the audio VAE.
8 months ago
ca9d300a80
Better estimation for memory usage during audio VAE encoding/decoding.
8 months ago
746a0410d4
Fix VAEEncode with taesd3.
8 months ago
04e8798c37
Improvements to the TAESD3 implementation.
8 months ago
df7db0e027
support TAESD3 ( #3738 )
8 months ago
bb1969cab7
Initial support for the stable audio open model.
8 months ago
69c8d6d8a6
Single and dual clip loader nodes support SD3.
...
You can use the CLIPLoader to use the t5xxl only or the DualCLIPLoader to
use CLIP-L and CLIP-G only for sd3.
9 months ago
0e49211a11
Load the SD3 T5xxl model in the same dtype stored in the checkpoint.
9 months ago
5889b7ca0a
Support multiple text encoder configurations on SD3.
9 months ago
8c4a9befa7
SD3 Support.
9 months ago
0920e0e5fe
Remove some unused imports.
9 months ago
comfyanonymous
ljleb
comfyanonymous
Alex "mcmonkey" Goodwin
Dr.Lt.Data