5bc6a0c650
fix: use correct parameter for upscale (fast)
2024-06-21 19:56:35 +02:00
51dc53b5c8
feat: save and output upscaled image with method fast in enhance
2024-06-20 02:49:22 +02:00
eada51dee4
feat: optimize progress bar, now correctly uses uov steps and overrides
2024-06-20 02:43:14 +02:00
4e575b9eb1
wip: add upscale or variation to enhance
2024-06-19 23:53:15 +02:00
87b3cec7d4
fix: download correct inpaint engine in enhance
2024-06-19 21:31:01 +02:00
22e1b08e4f
feat: add detection prompt dataset for quick selection
2024-06-19 00:58:55 +02:00
3b55e64990
fix: remove unused path_adetailer from config
2024-06-19 00:45:50 +02:00
cef92ffffe
Merge branch 'main_upstream' into feature/multi-step-rendering
2024-06-19 00:12:04 +02:00
6cb0b2143b
fix: correctly initialize inpaint_mask var, rename task styles index
2024-06-18 22:38:36 +02:00
dd866616bc
refactor: code cleanup
2024-06-18 22:16:48 +02:00
c0f7c3a8ee
feat: add erode or dilate and mask invert to enhance mask inpaint settings
2024-06-18 21:39:27 +02:00
229ff81738
refactor: rename max_num_boxes to max_detections
2024-06-18 21:07:27 +02:00
b7fb42436c
fix: correctly calculate current progress, display progressbar without any jumping
2024-06-18 12:35:41 +02:00
1175df843b
fix: correctly proceed progress bar within tasks
...
does not yet include jumping back for preparation steps
2024-06-18 11:48:42 +02:00
3567c04918
wip: refactor code to make it more efficient
...
now first processes all tasks and then does enhancements
2024-06-17 21:46:00 +02:00
65cc25e5bf
feat: add debug setting for enhance mask output
2024-06-16 22:54:44 +02:00
e300930298
feat: improve performance, do not reload the pipeline when prompts are the same as in the original task
2024-06-16 22:18:11 +02:00
33a9c156ad
fix: do not apply loras more than one time when not using lora in prompt
2024-06-16 21:40:39 +02:00
eeb1b79baa
feat: optimize prompt translation
2024-06-16 21:40:07 +02:00
9c93c18d0b
fix: process other models than sam when using enhance
2024-06-16 21:05:10 +02:00
ff3418876d
feat: refresh the whole pipeline, allows usage of inpaint and enhancement prompts
2024-06-16 20:44:35 +02:00
e1be3fa37a
Merge branch 'main' into feature/multi-step-rendering
2024-06-16 18:54:52 +02:00
cecd6876a5
Merge branch 'hotfix/add-missing-method-in-performance'
2024-06-16 18:54:42 +02:00
7c1a101c0f
hotfix: add missing method in performance enum ( #3154 )
2024-06-16 18:53:20 +02:00
9ef7fe0843
hotfix: add missing method in performance enum
2024-06-16 18:52:20 +02:00
b64d6d393c
fix: use != for literal comparison
2024-06-16 18:49:52 +02:00
9d41c9521b
fix: add workaround for same value in Steps IntEnum ( #3153 )
2024-06-16 18:44:16 +02:00
af209cda53
fix: add workaround for same value in Steps IntEnum
...
(cherry picked from commit ea1562d078
2024-06-16 18:41:17 +02:00
bf6820812f
feat: only process enhance when checkbox is set
...
similar to input image
2024-06-16 18:39:40 +02:00
ea1562d078
fix: add workaround for same value in Steps IntEnum
2024-06-16 17:46:48 +02:00
3e453501f7
fix: correctly identify and remove performance LoRA ( #3150 )
2024-06-16 16:52:58 +02:00
b947a5a4e6
fix: correctly identify and remove performance LoRA
...
(cherry picked from commit b3e4506009
2024-06-16 16:48:35 +02:00
b3e4506009
fix: correctly identify and remove performance LoRA
2024-06-16 16:48:12 +02:00
541fb2d445
feat: add support for enhance prompts
2024-06-16 15:58:27 +02:00
ef9fd293ff
wip: rename stage2 to enhance
2024-06-16 12:45:18 +02:00
8b21303542
wip: refactor UI for stage2
2024-06-15 01:38:22 +02:00
a71739026b
refactor: change wording of hint when nothing has been detected
2024-06-13 01:19:28 +02:00
f8f36828c7
feat: add disclaimer + skipping, stage2 won't properly work when used with inpaint or outpaint
2024-06-13 01:13:21 +02:00
dbc844804b
feat: add handling for stage2_mask_sam_max_num_boxes and config
2024-06-12 22:16:02 +02:00
9998b52dd2
feat: add gradio elements for input
2024-06-12 21:52:48 +02:00
190c4b0a6f
fix: do not set denoising_strength to async_worker dynamically
...
use parameter input and output
2024-06-12 21:51:49 +02:00
e055510f1b
fix: use correct mask dimensions
2024-06-11 00:12:02 +02:00
ead1ed617a
refactor: remove adetailer code
2024-06-10 23:46:25 +02:00
b8578a080a
fix: remove already declared config option
2024-06-10 20:46:25 +02:00
3873892b0a
feat: change default_inpaint_mask_sam_model to match sam model registry
2024-06-10 20:45:56 +02:00
ce1fb74270
feat: add download for sam models to config
2024-06-10 20:33:49 +02:00
8087861743
refactor: reorder inpaint_mask_sam_model by model size ascending
2024-06-09 18:46:18 +02:00
9affa32583
feat: set inpaint_respective_field manually
2024-06-09 01:36:32 +02:00
85b9005fa7
wip: adjust progressbar
2024-06-09 01:23:44 +02:00
5d8353eb74
fix: correctly reset pipeline
...
reset unet and inpaint worker after each adetailer task, improve memory efficiency
2024-06-09 01:10:11 +02:00
df70294a3e
wip: add adetailer
2024-06-08 23:30:45 +02:00
bb72938261
refactor: always use format width, height
2024-06-08 21:41:30 +02:00
c79f6bd461
refactor: move methods to handler scope
2024-06-08 20:33:47 +02:00
c1f62361ba
refactor: add EarlyReturnException to prevent return value issues
2024-06-08 20:25:50 +02:00
e58d913fbb
refactor: extract async_worker handle method into separate functions
2024-06-08 19:55:31 +02:00
9c352b6eb7
Merge branch 'main_upstream'
...
# Conflicts:
# fooocus_version.py
# modules/config.py
# modules/extra_utils.py
2024-06-06 19:50:15 +02:00
db36766f34
Merge branch 'fix/try-parse-env-var-strings-as-boolean'
...
# Conflicts:
# modules/config.py
2024-06-06 19:40:14 +02:00
5abae220c5
feat: parse env var strings to expected config value types ( #3107 )
...
* fix: add try_parse_bool for env var strings to enable config overrides of boolean values
* fix: fallback to given value if not parseable
* feat: extend eval to all valid types
* fix: remove return type
* fix: prevent strange type conversions by providing expected type
* feat: add tests
2024-06-06 19:29:08 +02:00
09be2c972c
fix: prevent strange type conversions by providing expected type
2024-06-06 19:13:17 +02:00
2186d3e15d
fix: remove return type
2024-06-06 18:38:58 +02:00
bef79e3cb4
feat: extend eval to all valid types
2024-06-06 18:37:00 +02:00
beab2b9d48
fix: fallback to given value if not parseable
2024-06-06 18:20:14 +02:00
c4faf2ae6c
fix: add try_parse_bool for env var strings to enable config overrides of boolean values
2024-06-06 18:05:55 +02:00
c8093ac1ca
Merge branch 'lllyasviel:main' into main
2024-06-06 14:03:19 +02:00
04d764820e
fix: correctly set alphas_cumprod ( #3106 )
2024-06-06 13:42:26 +02:00
b113eca87e
release: bump version to 2.4.2, update changelog
2024-06-05 21:58:51 +02:00
2d55a5f257
feat: add support for playground v2.5 ( #3073 )
...
* feat: add support for playground v2.5
* feat: add preset for playground v2.5
* feat: change URL to mashb1t
* feat: optimize playground v2.5 preset
2024-06-04 20:15:49 +02:00
cb24c686b0
Merge branch 'main_upstream' into develop_upstream
2024-06-04 20:11:42 +02:00
30b2a9536e
Merge branch 'feature/playground-2.5'
...
# Conflicts:
# modules/flags.py
2024-06-01 23:31:19 +02:00
778416c5e0
Merge branch 'main_upstream'
2024-06-01 23:25:21 +02:00
fe58df35c9
feat: add support for playground 2.5
2024-06-01 22:43:27 +02:00
7899261755
fix: turbo scheduler loading issue ( #3065 )
...
* fix: correctly load ModelPatcher
* feat: do not load model at all, not needed
2024-05-31 22:24:19 +02:00
4e658bb63a
feat: optimize performance lora filtering in metadata ( #3048 )
...
* feat: add remove_performance_lora method
* feat: use class PerformanceLoRA instead of strings in config
* refactor: cleanup flags, use __member__ to check if enums contains key
* feat: only filter lora of selected performance instead of all performance LoRAs
* fix: disable intermediate results for all restricted performances
too fast for Gradio, which becomes a bottleneck
* refactor: rename parse_json to to_json, rename parse_string to to_string
* feat: use speed steps as default instead of hardcoded 30
* feat: add method to_steps to Performance
* refactor: remove method ordinal_suffix, not needed anymore
* feat: only filter lora of selected performance instead of all performance LoRAs
both metadata and history log
* feat: do not filter LoRAs in metadata parser but rather in metadata load action
2024-05-30 16:14:28 +02:00
5768330142
Merge branch 'feature/optimize-performance-lora-filtering-in-metadata'
...
# Conflicts:
# modules/flags.py
# modules/util.py
# webui.py
2024-05-30 15:21:04 +02:00
2dca5ba638
feat: do not filter LoRAs in metadata parser but rather in metadata load action
2024-05-30 01:32:09 +02:00
91281e5561
feat: only filter lora of selected performance instead of all performance LoRAs
...
both metadata and history log
2024-05-30 00:22:31 +02:00
9c8ffbbe18
refactor: remove method ordinal_suffix, not needed anymore
2024-05-30 00:21:18 +02:00
1981ace9e1
feat: add method to_steps to Performance
2024-05-30 00:20:53 +02:00
f8f2455b65
feat: use speed steps as default instead of hardcoded 30
2024-05-30 00:20:23 +02:00
db8228d8f5
refactor: rename parse_json to to_json, rename parse_string to to_string
2024-05-30 00:19:35 +02:00
e3060e00d4
feat: only filter lora of selected performance instead of all performance LoRAs
2024-05-30 00:16:34 +02:00
55b01a81a6
refactor: cleanup flags, use __member__ to check if enums contains key
2024-05-30 00:14:27 +02:00
9564341fbd
feat: use class PerformanceLoRA instead of strings in config
2024-05-30 00:13:14 +02:00
4127fa410b
feat: add remove_performance_lora method
2024-05-30 00:11:07 +02:00
4361e7e629
Merge remote-tracking branch 'upstream/main'
2024-05-27 00:30:53 +02:00
dfff9b7dcf
fix: adjust clip skip default value from 1 to 2 ( #3011 )
...
* Revert "Revert "feat: add clip skip handling (#2999 )" (#3008 )"
This reverts commit 989a1ad52b
2024-05-27 00:28:22 +02:00
08877666ba
Merge branch 'main_upstream'
2024-05-26 22:14:20 +02:00
989a1ad52b
Revert "feat: add clip skip handling ( #2999 )" ( #3008 )
...
This reverts commit cc58fe5270
2024-05-26 22:07:44 +02:00
6dd718919c
feat: cleanup performance selection, make it completely dynamic
2024-05-26 18:09:22 +02:00
f82aa8a909
Merge branch 'develop_upstream'
...
# Conflicts:
# fooocus_version.py
# modules/util.py
# tests/test_utils.py
# webui.py
2024-05-26 15:28:08 +02:00
cc58fe5270
feat: add clip skip handling ( #2999 )
2024-05-26 14:18:19 +02:00
d850bca09f
feat: read value 'CFG Mimicking from TSNR' (adaptive_cfg) from presets ( #2990 )
2024-05-24 22:05:28 +02:00
04f64ab0bc
feat: add translation for image size describe ( #2992 )
2024-05-24 21:58:17 +02:00
302bfdf855
feat: read size and ratio of an image and provide the recommended size ( #2971 )
...
* Add the information about the size and ratio of the read image
* feat: use available aspect ratios from config, move function to util, change default visibility of label
* refactor: extract sdxl aspect ratios to flags, use in describe
as discussed in
https://github.com/lllyasviel/Fooocus/pull/2971#discussion_r1608493765
https://github.com/lllyasviel/Fooocus/pull/2971#issuecomment-2123620595
---------
Co-authored-by: Manuel Schmid <dev@mash1t.de>
Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com>
2024-05-22 20:47:44 +02:00
ebae829f43
Merge branch 'read-image-size'
...
# Conflicts:
# modules/util.py
# webui.py
2024-05-22 20:44:22 +02:00
751e867b37
refactor: extract sdxl aspect ratios to flags, use in describe
...
as discussed in
https://github.com/lllyasviel/Fooocus/pull/2971#discussion_r1608493765
https://github.com/lllyasviel/Fooocus/pull/2971#issuecomment-2123620595
2024-05-22 20:38:03 +02:00
311c445090
feat: use available aspect ratios from config, move function to util, change default visibility of label
2024-05-21 22:31:27 +02:00
7537612bcc
feat: only use valid inline loras, add subfolder support ( #2968 )
2024-05-20 19:21:41 +02:00
de1c77a923
Merge branch 'feature/inline-lora-optimisations-2'
...
# Conflicts:
# modules/util.py
# tests/test_utils.py
2024-05-20 19:19:33 +02:00
045d03ddad
feat: only use valid inline loras, add subfolder support
2024-05-20 19:08:35 +02:00
Manuel Schmid
Manuel Schmid
Manuel Schmid
Alexdnk
xhoxye