e99d97a9d9
Remove duplicated Reset View button ( #3865 )
...
* Remove duplicated Reset View button
* Disable flaky test
2024-06-26 01:23:55 -04:00
69d710e40f
Implement my alternative take on CFG++ as the euler_pp sampler.
...
Add euler_ancestral_pp which is the ancestral version of euler with the
same modification.
2024-06-25 07:41:52 -04:00
90aebb6c86
New Menu & Workflow Management ( #3112 )
...
* menu
* wip
* wip
* wip
* wip
* wip
* workflow saving/loading
* Support inserting workflows
Move buttosn to top of lists
* fix session storage
implement renaming
* temp
* refactor, better workflow instance management
* wip
* progress on progress
* added send to workflow
various fixes
* Support multiple image loaders
* Support dynamic size breakpoints based on content
* various fixes
add close unsaved warning
* Add filtering tree
* prevent renaming unsaved
* fix zindex on hover
* fix top offset
* use filename as workflow name
* resize on setting change
* hide element until it is drawn
* remove glow
* Fix export name
* Fix test, revert accidental changes to groupNode
* Fix colors on all themes
* show hover items on smaller screen (mobile)
* remove debugging code
* dialog fix
* Dont reorder open workflows
Allow elements around canvas
* Toggle body display on setting change
* Fix menu disappearing on chrome
* Increase delay when typing, remove margin on Safari, fix dialog location
* Fix overflow issue on iOS
* Add reset view button
Prevent view changes causing history entries
* Bottom menu wip
* Various fixes
* Fix merge
* Fix breaking old menu position
* Fix merge adding restore view to loadGraphData
2024-06-25 06:49:25 -04:00
eab211bb1e
Resample audio to 44100 when VAE encoding it.
2024-06-24 16:55:20 -04:00
866f54da8d
Add browser test action synced with TS repo ( #3852 )
...
* Add browser test action
* Add npm install task
2024-06-24 14:47:28 -04:00
73ca780019
Add SamplerEulerCFG++ node.
...
This node should match the DDIM implementation of CFG++ when "regular" is
selected.
"alternative" is a slightly different take on CFG++
2024-06-23 13:21:18 -04:00
2f360ae898
Support OneTrainer SD3 lora format.
2024-06-22 13:08:04 -04:00
4ef1479dcd
Multi dimension tiled scale function and tiled VAE audio encoding fallback.
2024-06-22 11:57:49 -04:00
887a6341ed
Proper ModelMergeSD3_2B node.
2024-06-21 08:41:31 -04:00
1e2839f4d9
More proper tiled audio decoding.
2024-06-20 16:50:31 -04:00
d5efde89b7
Add ipndm_v sampler, works best with the exponential scheduler.
2024-06-20 08:51:49 -04:00
45e10cac19
feat: add gits scheduler ( #3769 )
2024-06-20 08:12:15 -04:00
d7f0964266
Fix routes ( #3790 )
2024-06-19 22:36:31 -04:00
028a583bef
Fix issue with full diffusers SD3 loras.
2024-06-19 22:32:04 -04:00
0d6a57938e
Support loading diffusers SD3 model format with UNETLoader node.
2024-06-19 22:21:18 -04:00
b08a9dd04b
Remove empty line.
2024-06-19 20:20:35 -04:00
eee815ec99
Update sd1_clip.py ( #3684 )
...
Made token instance check more flexible so it also works with integers from numpy arrays or long tensors
2024-06-19 16:42:41 -04:00
e11052afcf
Add ipndm sampler.
2024-06-19 16:32:30 -04:00
97ae6ef460
Add api/ prefix to api endpoints ( #3779 )
2024-06-19 10:39:17 -04:00
3914d5a2ae
Support full SD3 loras.
2024-06-19 10:13:33 -04:00
55f0dc124e
Add soundfile dependency so that windows can save audio.
2024-06-18 09:57:40 -04:00
a45df69570
Basic tiled decoding for audio VAE.
2024-06-17 22:48:23 -04:00
379ff92e9e
fix app.js no graph defined ( #3754 )
...
* local test
* fix "graph" not found
* fix
---------
Co-authored-by: Xiujuan Li <xiujuali@amazon.com>
2024-06-17 07:56:53 -04:00
b7c473d1ab
Fix lora keys for SimpleTuner ( #3759 )
2024-06-17 07:55:06 -04:00
6425252c4f
Use fp16 as the default vae dtype for the audio VAE.
2024-06-16 13:12:54 -04:00
8ddc151a4c
Squash depreciation warning on new pytorch.
2024-06-16 13:06:23 -04:00
ca9d300a80
Better estimation for memory usage during audio VAE encoding/decoding.
2024-06-16 11:47:32 -04:00
746a0410d4
Fix VAEEncode with taesd3.
2024-06-16 03:10:04 -04:00
04e8798c37
Improvements to the TAESD3 implementation.
2024-06-16 02:04:24 -04:00
df7db0e027
support TAESD3 ( #3738 )
2024-06-16 02:03:53 -04:00
bb1969cab7
Initial support for the stable audio open model.
2024-06-15 12:14:56 -04:00
1281f933c1
Small optimization.
2024-06-15 02:44:38 -04:00
f2e844e054
Optimize some unneeded if conditions in the sampling code.
2024-06-15 02:26:19 -04:00
0ec513d877
Add a --force-channels-last to inference models in channel last mode.
2024-06-15 01:08:12 -04:00
0e06b370db
Print key names for easier debugging.
2024-06-14 18:18:53 -04:00
5eb98f0092
Exempt IPEX from non_blocking previews fixing segmentation faults. ( #3708 )
2024-06-13 18:51:14 -04:00
ac151ac169
Support SD3 diffusers lora.
2024-06-13 18:26:10 -04:00
37a08a41b3
Support setting weight offsets in weight patcher.
2024-06-13 17:21:26 -04:00
605e64f6d3
Fix lowvram issue.
2024-06-12 10:39:33 -04:00
0eaa34ec5b
Fix regular empty latent image not working with SD3 and custom sampler.
2024-06-12 10:32:34 -04:00
321e509e0a
Add link to SD3 example page to README.
2024-06-12 09:48:27 -04:00
c8b5e08dc3
Default shift value on SD3 is 3.0
2024-06-12 02:24:39 -04:00
1ddf512fdc
Don't auto convert clip and vae weights to fp16 when saving checkpoint.
2024-06-12 01:07:58 -04:00
32be358213
Save SD3 modelspec.architecture in CheckpointSave node.
2024-06-12 01:02:07 -04:00
694e0b48e0
SD3 better memory usage estimation.
2024-06-12 00:49:00 -04:00
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.
2024-06-11 23:27:39 -04:00
0e49211a11
Load the SD3 T5xxl model in the same dtype stored in the checkpoint.
2024-06-11 17:03:26 -04:00
5889b7ca0a
Support multiple text encoder configurations on SD3.
2024-06-11 13:14:43 -04:00
1c34d338d7
Update EmptySD3LatentImage to use 1024 resolution by default.
2024-06-11 07:37:22 -04:00
9424522ead
Reuse code.
2024-06-11 07:20:26 -04:00
Chenlei Hu
comfyanonymous
pythongosssss
Zhenyu Zhou
Mario Klingemann
Juanjuan
Janek Mann
Dr.Lt.Data
Simon Lui