Dr.Lt.Data
b5b99185ad
Merge branch 'comfyanonymous:master' into refactor/execution
2023-07-06 13:00:09 +09:00
comfyanonymous
ddc6f12ad5
Disable autocast in unet for increased speed.
2023-07-05 21:58:29 -04:00
comfyanonymous
603f02d613
Fix loras not working when loading checkpoint with config.
2023-07-05 19:42:24 -04:00
comfyanonymous
ccb1b25908
Add a conditioning concat node.
2023-07-05 17:40:22 -04:00
comfyanonymous
af7a49916b
Support loading unet files in diffusers format.
2023-07-05 17:38:59 -04:00
Dr.Lt.Data
80df372c9b
Merge branch 'comfyanonymous:master' into refactor/execution
2023-07-05 22:36:21 +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
06734b8ef5
Merge branch 'comfyanonymous:master' into refactor/execution
2023-07-04 15:31:10 +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
b3fd3c32ac
Merge branch 'comfyanonymous:master' into refactor/execution
2023-07-04 13:19:43 +09:00
comfyanonymous
3a09fac835
ConditioningAverage now also averages the pooled output.
2023-07-03 21:44:37 -04:00
Dr.Lt.Data
e3d819ae99
Merge branch 'Main' into execution
2023-07-04 10:08:29 +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
194c22264b
Merge branch 'comfyanonymous:master' into refactor/execution
2023-07-03 13:34:02 +09:00
comfyanonymous
dc9d1f31c8
Improvements for OSX.
2023-07-03 00:08:30 -04:00
Dr.Lt.Data
f6555e5f52
hotfix: ExecutionOneOf
...
- inefficient
2023-07-03 07:36:33 +09:00
Dr.Lt.Data
d0f1e5d05c
Merge branch 'comfyanonymous:master' into refactor/execution
2023-07-03 07:23:31 +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
c19652698d
Merge branch 'comfyanonymous:master' into refactor/execution
2023-07-02 14:42:09 +09:00
Dr.Lt.Data
8b57063602
support object_storage in IS_CHANGED
2023-07-02 14:40:49 +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
af55bb7a38
Merge branch 'comfyanonymous:master' into refactor/execution
2023-07-02 09:07:48 +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
Dr.Lt.Data
01ebdfecd3
bugfix: pass 'prompt' and 'extra_data' to get_input_data for determine IS_CHANGED
2023-07-01 16:18:05 +09:00
Dr.Lt.Data
fb54fda35f
Merge branch 'Main' into refactor/execution
2023-07-01 16:14:11 +09:00
comfyanonymous
fa1959e3ef
Fix nightly packaging.
2023-07-01 01:31:03 -04:00
Dr.Lt.Data
28e1856b5e
Merge branch 'refactor/execution' of https://github.com/ltdrdata/ComfyUI into refactor/execution
2023-07-01 11:06:45 +09:00
Dr.Lt.Data
10fb995928
object storage application fix2
2023-07-01 11:04:55 +09:00
Dr.Lt.Data
4c37e6f112
object storage application fix
2023-07-01 10:43:59 +09:00
Dr.Lt.Data
5372c5e8b5
object storage applied
2023-07-01 10:38:12 +09:00
Dr.Lt.Data
ddeb4aac35
Merge branch 'Main' into refactor/execution
2023-07-01 10:25:04 +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
9aed6cd94c
Merge branch 'comfyanonymous:master' into refactor/execution
2023-06-30 10:47:20 +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
9db03abcbd
Merge branch 'comfyanonymous:master' into refactor/execution
2023-06-29 17:35:16 +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
