happyz
/
Fooocus
mirror of https://github.com/lllyasviel/Fooocus.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
1,665 Commits 15 Branches 23 Tags 207 MiB
Commit Graph

48 Commits

Author SHA1 Message Date
Manuel Schmid b585d9dfa7
fix: correctly count sam masks 2024-06-16 15:57:53 +02:00
Manuel Schmid f8f36828c7
feat: add disclaimer + skipping, stage2 won't properly work when used with inpaint or outpaint 2024-06-13 01:13:21 +02:00
Manuel Schmid b5b33361c9
feat: only process sam_options.dino_erode_or_dilate when set 2024-06-10 23:47:09 +02:00
Manuel Schmid ead1ed617a
refactor: remove adetailer code 2024-06-10 23:46:25 +02:00
Manuel Schmid 29967d3a18
feat: add dino_erode_or_dilate and dino_debug again 2024-06-10 23:23:38 +02:00
Manuel Schmid 757863c023
feat: wrap sam model in model patcher for predict 2024-06-10 22:42:35 +02:00
Manuel Schmid 651f9c5cfd
refactor: rename box_erode_or_dilate to dino_erode_or_dilate, add option dino_debug 2024-06-10 20:47:22 +02:00
Manuel Schmid 3873892b0a
feat: change default_inpaint_mask_sam_model to match sam model registry 2024-06-10 20:45:56 +02:00
Manuel Schmid ce1fb74270
feat: add download for sam models to config 2024-06-10 20:33:49 +02:00
Manuel Schmid 8a81993940
wip: remove ultralytics, always use manual sam for image mask instead of rembg 2024-06-10 01:33:03 +02:00
Manuel Schmid 09e23f5509
refactor: add info to inpaint_mask_sam_prompt_text, rename variable for dino debugging 2024-06-09 23:09:46 +02:00
Manuel Schmid 57c049858c
feat: add debug dino and mask dilate and erode 2024-06-09 22:31:41 +02:00
Manuel Schmid ff9fa6c837
feat: add box_erode_or_dilate to generate_mask_from_image, expose more sam return values 2024-06-09 18:45:13 +02:00
Manuel Schmid df70294a3e
wip: add adetailer 2024-06-08 23:30:45 +02:00
Manuel Schmid bb72938261
refactor: always use format width, height 2024-06-08 21:41:30 +02:00
Manuel Schmid dd5a14ac7f
Merge branch 'feature/progress-bar' 
# Conflicts:
#	fooocus_version.py
#	modules/async_worker.py
#	webui.py
 2024-05-19 20:54:53 +02:00
Manuel Schmid 35b74dfa64
feat: optimize model management of image censoring (#2960) 
now follows general Fooocus model management principles + includes code optimisations for reusability
 2024-05-19 18:36:47 +02:00
Manuel Schmid 00d3d1b4b3
feat: add nsfw image censoring via config and checkbox (#958) 
* add nsfw image censoring

activatable via config, uses CompVis/stable-diffusion-safety-checker

* fix progressbar call for nsfw output

* use config to set cache dir for safety checker

* add checkbox black_out_nsfw

makes both enabling via config and checkbox possible, where config overrides the checkbox value

* fix: add missing diffusers package

* feat: extract safety checker, remove dependency to diffusers

* feat: make code compatible again after merge with main

* feat: move censor to extras, optimize safety checker file handling

* refactor: rename folder safety_checker_models to safety_checker
 2024-05-18 15:50:28 +02:00
Manuel Schmid d687ea73c4
Merge branch 'upstream/develop' 
# Conflicts:
#	webui.py
 2024-04-30 15:34:16 +02:00
Manuel Schmid 1dff430d4c
feat: update interposer from v3.1 to v4.0 (#2717) 
* fix: load image number from preset (#2611)

* fix: add default_image_number to preset handling

* fix: use minimum image number of preset and config to prevent UI overflow

* fix: use correct base dimensions for outpaint mask padding (#2612)

* fix: add Civitai compatibility for LoRAs in a1111 metadata scheme by switching schema (#2615)

* feat: update sha256 generation functions

29be1da7cf/modules/hashes.py

* feat: add compatibility for LoRAs in a1111 metadata scheme

* feat: add backwards compatibility

* refactor: extract remove_special_loras

* fix: correctly apply LoRA weight for legacy schema

* docs: bump version number to 2.3.1, add changelog (#2616)

* feat: update interposer vrom v3.1 to v4.0
 2024-04-06 15:27:35 +02:00
Manuel Schmid 056840c513
Merge commit '4945fc99624afc661aae2d3c5c5d73a32ba21897' 
# Conflicts:
#	fooocus_version.py
#	language/en.json
#	launch.py
#	modules/async_worker.py
#	modules/config.py
#	modules/flags.py
#	modules/meta_parser.py
#	modules/util.py
#	webui.py
 2024-03-02 17:24:53 +01:00
Manuel Schmid 5b7ddf8b22
feat: advanced params refactoring + prevent users from skipping/stopping other users tasks in queue (#981) 
* only make stop_button and skip_button interactive when rendering process starts

fix inconsistency in behaviour of stop_button and skip_button as it was possible to skip or stop other users processes while still being in queue

* use AsyncTask for last_stop handling instead of shared

* Revert "only make stop_button and skip_button interactive when rendering process starts"

This reverts commit d3f9156854.

* introduce state for task skipping/stopping

* fix return parameters of stop_clicked

* code cleanup, do not disable skip/stop on stop_clicked

* reset last_stop when skipping for further processing

* fix: replace fcbh with ldm_patched

* fix: use currentTask instead of ctrls after merging upstream

* feat: extract attribute disable_preview

* feat: extract attribute adm_scaler_positive

* feat: extract attribute adm_scaler_negative

* feat: extract attribute adm_scaler_end

* feat: extract attribute adaptive_cfg

* feat: extract attribute sampler_name

* feat: extract attribute scheduler_name

* feat: extract attribute generate_image_grid

* feat: extract attribute overwrite_step

* feat: extract attribute overwrite_switch

* feat: extract attribute overwrite_width

* feat: extract attribute overwrite_height

* feat: extract attribute overwrite_vary_strength

* feat: extract attribute overwrite_upscale_strength

* feat: extract attribute mixing_image_prompt_and_vary_upscale

* feat: extract attribute mixing_image_prompt_and_inpaint

* feat: extract attribute debugging_cn_preprocessor

* feat: extract attribute skipping_cn_preprocessor

* feat: extract attribute canny_low_threshold

* feat: extract attribute canny_high_threshold

* feat: extract attribute refiner_swap_method

* feat: extract freeu_ctrls attributes

freeu_enabled, freeu_b1, freeu_b2, freeu_s1, freeu_s2

* feat: extract inpaint_ctrls attributes

debugging_inpaint_preprocessor, inpaint_disable_initial_latent, inpaint_engine, inpaint_strength, inpaint_respective_field, inpaint_mask_upload_checkbox, invert_mask_checkbox, inpaint_erode_or_dilate

* wip: add TODOs

* chore: cleanup code

* feat: extract attribute controlnet_softness

* feat: extract remaining attributes, do not use globals in patch

* fix: resolve circular import, patch_all now in async_worker

* chore: cleanup pid code
 2024-02-24 19:01:06 +01:00
Manuel Schmid f8ca04a406
feat: add early return for prompt expansion when no new tokens should be added 
closes https://github.com/lllyasviel/Fooocus/issues/2278, also removes comma at the end added before tokenizer
 2024-02-19 15:22:10 +01:00
Manuel Schmid 9685a90090
Merge branch 'feature/add-inpaint-mask-generation' 2024-01-27 21:48:41 +01:00
rayronvictor dd5264dd14 fix error when run_grounded_sam find no boxes 2024-01-26 07:58:57 -03:00
Manuel Schmid 1ae495f6b8
Merge branch 'feature/add-inpaint-mask-generation' 
# Conflicts:
#	requirements_versions.txt
#	webui.py
 2024-01-26 11:32:53 +01:00
Manuel Schmid 62fe86f1e8
chore: always use cpu as default device 
this is overridden anyways
 2024-01-26 02:34:25 +01:00
Manuel Schmid d515d0f074
fix: remove unnecessary fp32 / fp16 handling 2024-01-26 02:06:17 +01:00
Manuel Schmid 90be73a6df
feat: add model patching 
automatically unload model when not needed anymore
 2024-01-26 02:05:38 +01:00
rayronvictor 228a0aaeea Add SAM support 2024-01-25 16:45:02 -03:00
Manuel Schmid 366984ca64
Merge branch 'feature/add-inpaint-mask-generation' 
# Conflicts:
#	webui.py
 2024-01-25 10:48:40 +01:00
rayronvictor f0fb9783e1 Add options to u2net_cloth_seg 2024-01-24 21:26:23 -03:00
Manuel Schmid e196a35ce2
Merge branch 'feature/add-inpaint-mask-generation' 
# Conflicts:
#	modules/config.py
#	requirements_versions.txt
 2024-01-24 02:46:09 +01:00
Manuel Schmid db5512fb93
feat: add inpaint mask generation functionality 
uses rembg, see https://github.com/danielgatis/rembg
 2024-01-24 02:22:50 +01:00
Manuel Schmid f3222b0f27
feat: extract attribute controlnet_softness 2024-01-22 20:09:24 +01:00
Manuel Schmid 2d8ca41ce5
feat: extract attribute canny_high_threshold 2024-01-22 19:08:54 +01:00
Manuel Schmid ec486443ea
feat: extract attribute canny_low_threshold 2024-01-22 19:06:10 +01:00
lllyasviel 0c4f20a0d2
try fix #1761 again (#1680) 2023-12-31 04:38:31 -08:00
lllyasviel 2521af308b
try fix #1671 (#1678) 2023-12-31 03:38:16 -08:00
lllyasviel 0e1aa8d084
better caster (#1480) 
related to mps/rocm/cpu casting for fp16 and etc on clip
 2023-12-17 17:09:15 -08:00
lllyasviel ec5dd950a2
Fix many precision problems 
Many users reported that image quality is different from 2.1.824. We reviewed all codes and fixed several precision problems in 2.1.846.
 2023-12-16 15:55:53 -08:00
lllyasviel 3a727fd240
2.1.844 
* maintain clip vision device
* update links in troubleshoot
 2023-12-16 10:34:47 -08:00
lllyasviel 5b99e3a1e4
2.1.839 2023-12-13 21:14:50 -08:00
lllyasviel fcc7458d15 Avoid tokenizer download from torch hub 2023-12-13 08:25:44 -08:00
lllyasviel 406133f0fb safer link 2023-12-12 21:53:13 -08:00
lllyasviel 322aa5a724 use our blip 2023-12-12 21:07:39 -08:00
lllyasviel f8e651a483 [2.1.831] Fooocus Describe 2023-12-12 19:34:18 -08:00
lllyasviel e8d88d3e25 2.1.826 2023-12-12 11:38:05 -08:00