4932 commits

Author	SHA1	Message	Date
Won-Kyu Park	4c937cbfab	Merge 310d0e6938 into fd68e0c384	2025-12-20 22:18:57 +03:00
w-e-w	fd68e0c384	update stable_diffusion_repo url (#17207)	2025-12-18 09:41:31 -05:00
silvertuanzi	6685e532df	fix uv on linux (#17139)	2025-10-07 16:06:10 -04:00
namemechan	e0be7a8427	update sd_hijack_optimizations.py — Changing [CUDA Compute Capability] Version	2025-09-17 20:23:19 +09:00
Jan Alexander Steffens	2174ce5afe	Fix Beta sampling to match the paper (#16926)	2025-05-03 02:17:03 -04:00
Nick Richardson	ebbc56b4ec	Add random number generator source to filename (#16928)	2025-05-02 13:02:05 -04:00
w-e-w	3064b21e23	PyTorch 2.7.0 xFormers 0.0.30 (#16972)	2025-05-01 12:57:46 -04:00
w-e-w	374bb6cc38	Python 3.9 annotation compatibility (#16852)	2025-03-04 11:11:26 -05:00
w-e-w	435b1df2db	remove assert, original run with original args	2025-03-01 00:17:49 +09:00
w-e-w	7fd7fc67f7	add -I to uv BAD_FLAGS	2025-02-28 23:53:11 +09:00
w-e-w	9d1accfea0	fallback to pip if uv failes	2025-02-28 23:53:11 +09:00
w-e-w	c59a2badd2	auto install uv	2025-02-28 23:53:11 +09:00
Haoming	9f670bc7e8	uv hook	2025-02-28 19:25:35 +08:00
w-e-w	32595360f2	fix old hash digits (#16845)	2025-02-15 10:49:48 -05:00
w-e-w	8c7bc08f60	Old hash from cache (#16830) ... * use not equal when comparing mtime * cache partial hash aka old hash Co-Authored-By: npc-riddlah <84955385+npc-riddlah@users.noreply.github.com> --------- Co-authored-by: npc-riddlah <84955385+npc-riddlah@users.noreply.github.com>	2025-02-10 02:14:32 -05:00
w-e-w	57e15ec9b5	Blackwell compatibility (Windows only) (#16817)	2025-01-30 12:36:02 -05:00
w-e-w	f25c3fc9cb	fix sd_vae_explanation (#16748)	2024-12-24 15:43:55 -05:00
Alexander Sachenko	b414c62ce4	removed unnecessary import modules.errors	2024-12-24 15:45:10 +03:00
w-e-w	04903af798	Merge pull request #16604 from Haoming02/ext-updt-parallel ... Check for Extension Updates in Parallel	2024-12-18 03:21:48 +09:00
w-e-w	0120768f63	Merge pull request #16687 from Haoming02/dropdown4format ... Use gr.Dropdown for Image Formats	2024-11-28 17:39:12 +09:00
w-e-w	b425b97ad6	improve img fromat description	2024-11-28 17:14:03 +09:00
w-e-w	539ea3982d	use DropdownEditable ... use DropdownEditable so user can input other formats if they require it make the default png the first on the list	2024-11-28 14:10:44 +09:00
Haoming	65bd61e87c	format-dropdown	2024-11-27 10:42:50 +08:00
catboxanon	ca3bedbd02	Honor lossless webp compression option in API	2024-11-01 11:32:52 -04:00
Won-Kyu Park	1d3dae1471	task manager added ... based on https://github.com/lllyasviel/stable-diffusion-webui-forge/blob/main/modules_forge/main_thread.py * classified * this way, gc.collect() will work as intended.	2024-11-01 12:36:09 +09:00
Won-Kyu Park	98cb284eb1	flux: clean up some dead code	2024-11-01 12:35:37 +09:00
Won-Kyu Park	4ad5f22c7b	do not use assing=True for nn.LayerNorm	2024-11-01 12:35:36 +09:00
Won-Kyu Park	5f3314ec43	do not use copy option for nn.Embedding	2024-11-01 12:35:36 +09:00
Won-Kyu Park	ba499f92ac	use shared.opts.lora_without_backup_weight option in the devices.autocast() ... * add nn.Embedding in the devices.autocast() * do not cast forward args for some cases * add copy option in the devices.autocast()	2024-11-01 12:35:36 +09:00
Won-Kyu Park	03516f48f0	use isinstance()	2024-11-01 12:35:35 +09:00
Won-Kyu Park	2e6533519b	fix some nn.Embedding to set dtype=float32 for some float8 freeze model	2024-11-01 12:35:35 +09:00
Won-Kyu Park	8c9c139c65	support Flux schnell and cleanup	2024-11-01 12:35:34 +09:00
Won-Kyu Park	11c9bc719c	make Sd3T5 shared.opts.sd3_enable_t5 independent	2024-11-01 12:35:34 +09:00
Won-Kyu Park	4bea93bc06	fixed typo in the flux lora map	2024-11-01 12:35:33 +09:00
Won-Kyu Park	28eca46959	fix flux to use float8 t5xxl	2024-11-01 12:35:32 +09:00
Won-Kyu Park	f569f6eb1e	use text_encoders.t5xxl.transformer.shared.weight tokens weights ... * some T5XXL do not have encoder.embed_tokens.weight. use shared.weight embed_tokens instead. * use float8 text encoder t5xxl_fp8_e4m3fn.safetensors	2024-11-01 12:35:29 +09:00
Won-Kyu Park	71b430f703	call torch_gc() to fix VRAM usage spike when call decode_first_stage()	2024-11-01 12:34:44 +09:00
Won-Kyu Park	380e9a84c3	call lowvram.send_everything_to_cpu() for interrupted case	2024-11-01 12:34:42 +09:00
Won-Kyu Park	6675d1f090	use assign=True for some cases	2024-11-01 12:34:38 +09:00
Won-Kyu Park	eee7294200	add fix_unet_prefix() to support unet only checkpoints	2024-11-01 12:34:36 +09:00
Won-Kyu Park	1318f6118e	fix load_vae() to check size mismatch	2024-11-01 12:34:34 +09:00
Won-Kyu Park	1e73a28707	fix for float8_e5m2 freeze model	2024-11-01 12:34:32 +09:00
Won-Kyu Park	2ffdf01e05	fix position_ids	2024-11-01 12:34:30 +09:00
Won-Kyu Park	3b18b6f482	revert to use without_autocast()	2024-11-01 12:34:28 +09:00
Won-Kyu Park	44a8480f0c	minor update ... * use dtype_inference	2024-11-01 12:34:22 +09:00
Won-Kyu Park	789bfc7db4	add cheap approximation for flux	2024-11-01 12:34:20 +09:00
Won-Kyu Park	9e57c722b2	fix to support float8_*	2024-11-01 12:34:18 +09:00
Won-Kyu Park	219a0e2429	support Flux1	2024-11-01 12:34:16 +09:00
Won-Kyu Park	9c0fd83b5e	vae fix for flux	2024-11-01 12:34:14 +09:00
Won-Kyu Park	7e2d51965f	fix for t5xxl	2024-11-01 12:34:12 +09:00