comfyanonymous
7c94219393
Fix bundled embed.
2024-08-07 13:30:45 -04:00
comfyanonymous
a6d6c2d378
Support for "Comfy" lora format.
...
The keys are just: model.full.model.key.name.lora_up.weight
It is supported by all comfyui supported models.
Now people can just convert loras to this format instead of having to ask
for me to implement them.
2024-08-07 13:18:32 -04:00
comfyanonymous
3e01ab3a66
Controlnet code refactor.
2024-08-07 12:59:28 -04:00
comfyanonymous
04f70b853e
Support format for embeddings bundled in loras.
2024-08-07 03:45:25 -04:00
comfyanonymous
001ff4d6a6
Fix OOMs happening in some cases.
...
A cloned model patcher sometimes reported a model was loaded on a device
when it wasn't.
2024-08-06 13:36:04 -04:00
comfyanonymous
5228fbf0ad
Unload models and load them back in lowvram mode no free vram.
2024-08-06 03:22:39 -04:00
comfyanonymous
bcb4848096
Flux tweak memory usage.
2024-08-05 21:58:28 -04:00
comfyanonymous
f7183e2c73
Improve performance on some lowend GPUs.
2024-08-05 16:24:04 -04:00
a-One-Fan
2e56b50183
Fix Flux FP64 math on XPU ( #4210 )
2024-08-05 01:26:20 -04:00
comfyanonymous
261c6ba855
Support simple diffusers Flux loras.
2024-08-04 22:05:48 -04:00
Silver
b87a10e5f1
Correct spelling 'token_weight_pars_t5' to 'token_weight_pairs_t5' ( #4200 )
2024-08-04 17:10:02 -04:00
comfyanonymous
8e7aa23b6a
ONNX tracing fixes.
2024-08-04 15:45:43 -04:00
comfyanonymous
85fadea55c
Fix issue with some custom nodes.
2024-08-04 10:03:33 -04:00
comfyanonymous
10ad73d520
Fix crash.
2024-08-03 16:55:38 -04:00
comfyanonymous
e7287d2fc2
Tweak lowvram memory formula.
2024-08-03 16:44:50 -04:00
comfyanonymous
d4ca060482
Lower lowvram memory to 1/3 of free memory.
2024-08-03 15:14:07 -04:00
comfyanonymous
f27f0f8a48
Fix some issues.
2024-08-03 15:06:40 -04:00
comfyanonymous
e83d97d649
Cap lowvram to half of free memory.
2024-08-03 14:50:20 -04:00
comfyanonymous
753d9640f9
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.
2024-08-03 13:45:19 -04:00
comfyanonymous
2181bb7a57
Load T5 in fp8 if it's in fp8 in the Flux checkpoint.
2024-08-03 12:39:33 -04:00
comfyanonymous
2878ffd75a
More aggressive batch splitting.
2024-08-03 11:53:30 -04:00
comfyanonymous
b0eaa09c6a
Better per model memory usage estimations.
2024-08-02 18:09:24 -04:00
comfyanonymous
e2284e5609
Tweak regular SD memory formula.
2024-08-02 17:34:30 -04:00
comfyanonymous
ebc7233402
Better Flux vram estimation.
2024-08-02 17:02:35 -04:00
Alexander Brown
90267ffb3a
Fix clip_g/clip_l mixup ( #4168 )
2024-08-01 21:40:56 -04:00
comfyanonymous
a06d0ff763
Hack to make all resolutions work on Flux models.
2024-08-01 21:39:18 -04:00
comfyanonymous
49c0c333d3
Tweak the memory usage formulas for Flux and SD.
2024-08-01 17:53:45 -04:00
comfyanonymous
f176649e08
Make ComfyUI split batches a higher priority than weight offload.
2024-08-01 16:39:59 -04:00
comfyanonymous
516d71d227
Fast preview support for Flux.
2024-08-01 16:28:11 -04:00
comfyanonymous
f5b2fc6e6b
Fix bfloat16 potentially not being enabled on mps.
2024-08-01 16:18:44 -04:00
comfyanonymous
bd6f023ff6
Try to fix mac issue.
2024-08-01 13:41:27 -04:00
comfyanonymous
5606d85b07
Add a way to load the diffusion model in fp8 with UNETLoader node.
2024-08-01 13:30:51 -04:00
comfyanonymous
30a15dd5e1
Better Mac support on flux model.
2024-08-01 13:10:50 -04:00
comfyanonymous
faad5f1cdb
Make lowvram more aggressive on low memory machines.
2024-08-01 12:11:57 -04:00
comfyanonymous
5d5b9dcf89
Fix .sft file loading (they are safetensors files).
2024-08-01 11:32:58 -04:00
comfyanonymous
d6d48306d8
Load flux t5 in fp8 if weights are in fp8.
2024-08-01 11:05:56 -04:00
comfyanonymous
96dbbd23d8
Fix old python versions no longer working.
2024-08-01 09:57:20 -04:00
comfyanonymous
fc6a27f36c
Basic Flux Schnell and Flux Dev model implementation.
2024-08-01 09:49:29 -04:00
comfyanonymous
339a710a7a
Mac supports bf16 just make sure you are using the latest pytorch.
2024-08-01 09:42:17 -04:00
comfyanonymous
78c273b0ba
Make lowvram less aggressive when there are large amounts of free memory.
2024-08-01 03:58:58 -04:00
comfyanonymous
a4b37c2939
Fix to get fp8 working on T5 base.
2024-07-31 02:00:19 -04:00
comfyanonymous
c5b754fbb6
Fix hunyuan dit text encoder weights always being in fp32.
2024-07-31 01:34:57 -04:00
comfyanonymous
4e9abfb0d5
Lower CLIP memory usage by a bit.
2024-07-31 01:32:35 -04:00
comfyanonymous
7f0000bc5a
Lower T5 memory usage by a few hundred MB.
2024-07-31 00:52:34 -04:00
comfyanonymous
671fba8c0d
Fix potential issue with non clip text embeddings.
2024-07-30 14:41:13 -04:00
comfyanonymous
36b0b2b215
Use common function for casting weights to input.
2024-07-30 10:49:14 -04:00
comfyanonymous
d0cc951625
Remove unnecessary code.
2024-07-30 05:01:34 -04:00
comfyanonymous
7f112b9d5d
Improve artifacts on hydit, auraflow and SD3 on specific resolutions.
...
This breaks seeds for resolutions that are not a multiple of 16 in pixel
resolution by using circular padding instead of reflection padding but
should lower the amount of artifacts when doing img2img at those
resolutions.
2024-07-29 20:48:50 -04:00
comfyanonymous
79ea2d3d12
Refactor: Move sd2_clip.py to text_encoders folder.
2024-07-28 01:19:20 -04:00
comfyanonymous
f4a8f8db50
Don't treat Bert model like CLIP.
...
Bert can accept up to 512 tokens so any prompt with more than 77 should
just be passed to it as is instead of splitting it up like CLIP.
2024-07-26 13:08:12 -04:00
