Dr.Lt.Data
1486e227f7
Merge branch 'comfyanonymous:master' into feature/settings
2023-07-05 22:36:09 +09:00
comfyanonymous
e57cba4c61
Add gpu variations of the sde samplers that are less deterministic
...
but faster.
2023-07-05 01:39:38 -04:00
comfyanonymous
f81b192944
Add logit scale parameter so it's present when saving the checkpoint.
2023-07-04 23:01:28 -04:00
comfyanonymous
acf95191ff
Properly support SDXL diffusers loras for unet.
2023-07-04 21:15:23 -04:00
Dr.Lt.Data
d8116d90cd
Merge branch 'comfyanonymous:master' into feature/settings
2023-07-04 15:30:54 +09:00
comfyanonymous
8d694cc450
Fix issue with OSX.
2023-07-04 02:09:02 -04:00
comfyanonymous
c02f3baeaf
Now the model merge blocks node will use the longest match.
2023-07-04 00:51:17 -04:00
Dr.Lt.Data
b35ae9d6b9
Merge branch 'comfyanonymous:master' into feature/settings
2023-07-04 13:19:28 +09:00
comfyanonymous
3a09fac835
ConditioningAverage now also averages the pooled output.
2023-07-03 21:44:37 -04:00
Dr.Lt.Data
72990ee75b
Merge branch 'comfyanonymous:master' into feature/settings
2023-07-04 09:24:39 +09:00
comfyanonymous
d94ddd8548
Add text encode nodes to control the extra parameters in SDXL.
2023-07-03 19:11:36 -04:00
comfyanonymous
c3e96e637d
Pass device to CLIP model.
2023-07-03 16:09:37 -04:00
comfyanonymous
5e6bc824aa
Allow passing custom path to clip-g and clip-h.
2023-07-03 15:45:04 -04:00
Dr.Lt.Data
87294ffdd7
Merge branch 'comfyanonymous:master' into feature/settings
2023-07-03 13:33:49 +09:00
comfyanonymous
dc9d1f31c8
Improvements for OSX.
2023-07-03 00:08:30 -04:00
Dr.Lt.Data
4a53754708
Merge branch 'comfyanonymous:master' into feature/settings
2023-07-03 07:23:18 +09:00
comfyanonymous
103c487a89
Cleanup.
2023-07-02 11:58:23 -04:00
comfyanonymous
ae948b42fa
Add taesd weights to standalones.
2023-07-02 11:47:30 -04:00
comfyanonymous
2c4e0b49b7
Switch to fp16 on some cards when the model is too big.
2023-07-02 10:00:57 -04:00
Dr.Lt.Data
5ffaabe8ec
Merge branch 'comfyanonymous:master' into feature/settings
2023-07-02 14:41:58 +09:00
comfyanonymous
6f3d9f52db
Add a --force-fp16 argument to force fp16 for testing.
2023-07-01 22:42:35 -04:00
Dr.Lt.Data
81902c4762
Merge branch 'comfyanonymous:master' into feature/settings
2023-07-02 09:07:36 +09:00
comfyanonymous
1c1b0e7299
--gpu-only now keeps the VAE on the device.
2023-07-01 15:22:40 -04:00
comfyanonymous
ce35d8c659
Lower latency by batching some text encoder inputs.
2023-07-01 15:07:39 -04:00
comfyanonymous
3b6fe51c1d
Leave text_encoder on the CPU when it can handle it.
2023-07-01 14:38:51 -04:00
comfyanonymous
b6a60fa696
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
97ee230682
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
fa1959e3ef
Fix nightly packaging.
2023-07-01 01:31:03 -04:00
Dr.Lt.Data
d2bf7fd618
Merge branch 'Main' into feature/settings
2023-07-01 11:15:13 +09:00
comfyanonymous
9f2986318f
Move model merging nodes to advanced and add to readme.
2023-06-30 15:21:55 -04:00
comfyanonymous
5a9ddf94eb
LoraLoader node now caches the lora file between executions.
2023-06-29 23:40:51 -04:00
comfyanonymous
6e9f28401f
Persist node instances between executions instead of deleting them.
...
If the same node id with the same class exists between two executions the
same instance will be used.
This means you can now cache things in nodes for more efficiency.
2023-06-29 23:38:56 -04:00
Dr.Lt.Data
ca74305136
Merge branch 'comfyanonymous:master' into feature/settings
2023-06-30 10:47:05 +09:00
comfyanonymous
9920367d3c
Fix embeddings not working with --gpu-only
2023-06-29 20:43:06 -04:00
comfyanonymous
62db11683b
Move unet to device right after loading on highvram mode.
2023-06-29 20:43:06 -04:00
Dr.Lt.Data
1ce0f3044e
Merge branch 'comfyanonymous:master' into feature/settings
2023-06-29 17:35:00 +09:00
reaper47
e7ed507d3d
Add link to 7z in README ( #809 )
...
* Add link to 7z in README
* Change 7z to 7-Zip
2023-06-29 04:09:59 -04:00
comfyanonymous
4376b125eb
Remove useless code.
2023-06-29 00:26:33 -04:00
comfyanonymous
89120f1fbe
This is unused but it should be 1280.
2023-06-28 18:04:23 -04:00
Dr.Lt.Data
9ef244e374
Merge branch 'comfyanonymous:master' into feature/settings
2023-06-28 15:54:28 +09:00
comfyanonymous
2c7c14de56
Support for SDXL text encoder lora.
2023-06-28 02:22:49 -04:00
comfyanonymous
fcef47f06e
Fix bug.
2023-06-28 00:38:07 -04:00
comfyanonymous
2d880fec3a
Add a node to zero out the cond to advanced/conditioning
...
The stability streamlit example passes a zero cond as the negative input
so using this for the negative input makes outputs match the streamlit.
2023-06-27 23:30:52 -04:00
Dr.Lt.Data
f2cd7fce10
Merge branch 'comfyanonymous:master' into feature/settings
2023-06-27 14:55:47 +09:00
comfyanonymous
50abf7c938
Merge branch 'patch-1' of https://github.com/jjangga0214/ComfyUI
2023-06-27 01:42:16 -04:00
Dr.Lt.Data
0a8dad06eb
Merge branch 'comfyanonymous:master' into feature/settings
2023-06-27 09:21:50 +09:00
comfyanonymous
8248babd44
Use pytorch attention by default on nvidia when xformers isn't present.
...
Add a new argument --use-quad-cross-attention
2023-06-26 13:03:44 -04:00
comfyanonymous
9b93b920be
Add CheckpointSave node to save checkpoints.
...
The created checkpoints contain workflow metadata that can be loaded by
dragging them on top of the UI or loading them with the "Load" button.
Checkpoints will be saved in fp16 or fp32 depending on the format ComfyUI
is using for inference on your hardware. To force fp32 use: --force-fp32
Anything that patches the model weights like merging or loras will be
saved.
The output directory is currently set to: output/checkpoints but that might
change in the future.
2023-06-26 12:22:27 -04:00
Dr.Lt.Data
34c6f075ce
Merge branch 'comfyanonymous:master' into feature/settings
2023-06-26 22:28:32 +09:00
comfyanonymous
b72a7a835a
Support loras based on the stability unet implementation.
2023-06-26 02:56:11 -04:00
