comfyanonymous
c17cfd126d
Fix typo.
2023-07-19 10:20:32 -04:00
comfyanonymous
d71acc2fe4
Fix ddim issue with older torch versions.
2023-07-19 10:16:00 -04:00
comfyanonymous
3aad28d483
Add MX450 and MX550 to list of cards with broken fp16.
2023-07-19 03:08:30 -04:00
comfyanonymous
4ec7f09adc
It's actually possible to torch.compile the unet now.
2023-07-18 21:36:35 -04:00
comfyanonymous
cea5c2adfb
Add key to indicate checkpoint is v_prediction when saving.
2023-07-18 00:25:53 -04:00
comfyanonymous
22abe3af9f
Fix device print on old torch version.
2023-07-17 15:18:58 -04:00
comfyanonymous
5108099f0c
Enable --cuda-malloc by default on torch 2.0 and up.
...
Add --disable-cuda-malloc to disable it.
2023-07-17 15:12:10 -04:00
comfyanonymous
7da7500fcc
--windows-standalone-build now enables --cuda-malloc
2023-07-17 14:10:36 -04:00
comfyanonymous
5ddb2ca26f
Add a command line argument to enable backend:cudaMallocAsync
2023-07-17 11:00:14 -04:00
comfyanonymous
f9688727f1
Only calculate randn in some samplers when it's actually being used.
2023-07-17 10:11:08 -04:00
comfyanonymous
244987af7e
Fix regression with ddim and uni_pc when batch size > 1.
2023-07-17 09:35:19 -04:00
comfyanonymous
debccdc6f9
Refactor of sampler code to deal more easily with different model types.
2023-07-17 01:22:12 -04:00
comfyanonymous
ba6e888eb9
Lower lora ram usage when in normal vram mode.
2023-07-16 02:59:04 -04:00
comfyanonymous
73c2afbe44
Speed up lora loading a bit.
2023-07-15 13:25:22 -04:00
comfyanonymous
f67f1c99b8
Fix CLIPSetLastLayer not reverting when removed.
2023-07-15 01:41:21 -04:00
comfyanonymous
26da73b600
Reduce floating point rounding errors in loras.
2023-07-15 00:53:00 -04:00
comfyanonymous
daac253452
Add a node to merge CLIP models.
2023-07-14 02:41:18 -04:00
comfyanonymous
f4c18db4ed
Prevent the clip_g position_ids key from being saved in the checkpoint.
...
This is to make it match the official checkpoint.
2023-07-12 20:15:02 -04:00
comfyanonymous
28bf6d49da
Fix potential tensors being on different devices issues.
2023-07-12 19:29:27 -04:00
comfyanonymous
6e99974161
Support SDXL embedding format with 2 CLIP.
2023-07-10 10:34:59 -04:00
comfyanonymous
c1c170f61a
Don't patch weights when multiplier is zero.
2023-07-09 17:46:56 -04:00
comfyanonymous
55d00ccefd
latent2rgb matrix for SDXL.
2023-07-09 13:59:09 -04:00
comfyanonymous
42805fd416
Empty cache after model unloading for normal vram and lower.
2023-07-09 09:56:03 -04:00
comfyanonymous
7d69d770e1
Support loading clip_g from diffusers in CLIP Loader nodes.
2023-07-09 09:33:53 -04:00
comfyanonymous
c5779f04aa
Fix merging not working when model2 of model merge node was a merge.
2023-07-08 22:31:10 -04:00
comfyanonymous
4685d2b07f
Merge branch 'condmask-fix' of https://github.com/vmedea/ComfyUI
2023-07-07 01:52:25 -04:00
comfyanonymous
9caaa09c71
Add arguments to run the VAE in fp16 or bf16 for testing.
2023-07-06 23:23:46 -04:00
comfyanonymous
d3b3c94616
Fix bug with weights when prompt is long.
2023-07-06 02:43:40 -04:00
comfyanonymous
fa8010f038
Disable autocast in unet for increased speed.
2023-07-05 21:58:29 -04:00
comfyanonymous
c6391df3a5
Fix loras not working when loading checkpoint with config.
2023-07-05 19:42:24 -04:00
comfyanonymous
2ff6108df3
Support loading unet files in diffusers format.
2023-07-05 17:38:59 -04:00
comfyanonymous
56d999484b
Add gpu variations of the sde samplers that are less deterministic
...
but faster.
2023-07-05 01:39:38 -04:00
comfyanonymous
7ffb8dbe56
Add logit scale parameter so it's present when saving the checkpoint.
2023-07-04 23:01:28 -04:00
comfyanonymous
60bdf7c00b
Properly support SDXL diffusers loras for unet.
2023-07-04 21:15:23 -04:00
mara
386e66bd7f
Fix size check for conditioning mask
...
The wrong dimensions were being checked, [1] and [2] are the image size.
not [2] and [3]. This results in an out-of-bounds error if one of them
actually matches.
2023-07-04 16:34:42 +02:00
comfyanonymous
06ce99e525
Fix issue with OSX.
2023-07-04 02:09:02 -04:00
comfyanonymous
fcee7e88db
Pass device to CLIP model.
2023-07-03 16:09:37 -04:00
comfyanonymous
be891646cd
Allow passing custom path to clip-g and clip-h.
2023-07-03 15:45:04 -04:00
comfyanonymous
fd93e324e8
Improvements for OSX.
2023-07-03 00:08:30 -04:00
comfyanonymous
033dc1f52a
Cleanup.
2023-07-02 11:58:23 -04:00
comfyanonymous
280a4e3544
Switch to fp16 on some cards when the model is too big.
2023-07-02 10:00:57 -04:00
comfyanonymous
dd4abf1345
Add a --force-fp16 argument to force fp16 for testing.
2023-07-01 22:42:35 -04:00
comfyanonymous
1e24a78d85
--gpu-only now keeps the VAE on the device.
2023-07-01 15:22:40 -04:00
comfyanonymous
5ace1146c5
Lower latency by batching some text encoder inputs.
2023-07-01 15:07:39 -04:00
comfyanonymous
2ee0aa317c
Leave text_encoder on the CPU when it can handle it.
2023-07-01 14:38:51 -04:00
comfyanonymous
d5a7abe10d
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.
2023-07-01 13:28:07 -04:00
comfyanonymous
e946dca0e1
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.
2023-07-01 12:37:23 -04:00
comfyanonymous
7dff6c094c
LoraLoader node now caches the lora file between executions.
2023-06-29 23:40:51 -04:00
comfyanonymous
7520fc3eac
Fix embeddings not working with --gpu-only
2023-06-29 20:43:06 -04:00
comfyanonymous
790073a21d
Move unet to device right after loading on highvram mode.
2023-06-29 20:43:06 -04:00
