5452bc6ac3
All Forge Spaces Now Pass 4GB VRAM
...
and they all 100% reproduce author results
2024-08-20 08:01:10 -07:00
f136f86fee
Merge pull request #1340 from DenOfEquity/fix-for-new-samplers
...
Fix for new samplers
2024-08-20 10:12:37 -04:00
c127e60cf0
Update sd_samplers_kdiffusion.py
...
add new samplers here
2024-08-20 15:01:58 +01:00
8c7db614ba
Update alter_samplers.py
...
move new samplers from here
2024-08-20 15:00:56 +01:00
14ac95f908
fix
2024-08-20 01:37:01 -07:00
6f411a4940
fix loras on nf4 models when activate "loras in fp16"
2024-08-20 01:29:52 -07:00
65ec461f8a
revise space
2024-08-19 22:43:09 -07:00
fef6df29d9
Update README.md
2024-08-19 22:33:20 -07:00
6c7c85628e
change News to Quick List
2024-08-19 22:30:56 -07:00
5ecc525664
fix #1322
2024-08-19 20:19:13 -07:00
475524496d
revise
2024-08-19 18:54:54 -07:00
8eeeace725
Merge pull request #1316 from lllyasviel/more_samplers1
...
Add samplers: HeunPP2, IPDNM, IPNDM_V, DEIS
2024-08-19 20:49:37 -04:00
2fc1708a59
Add samplers: HeunPP2, IPDNM, IPNDM_V, DEIS
...
Pending: CFG++ Samplers, ODE Samplers
The latter is probably easy to implement, the former needs modifications in sd_samplers_cfg_denoiser.py
2024-08-19 20:48:41 -04:00
9bc2d04ca9
Merge pull request #1310 from lllyasviel/more_schedulers
...
Add Align Your Steps GITS, AYS 11 Steps and AYS 32 Steps Schedulers.
2024-08-19 16:58:52 -04:00
9f5a27ca4e
Add Align Your Steps GITS, AYS 11 Steps and AYS 32 Steps Schedulers.
2024-08-19 16:57:58 -04:00
d7151b4dcd
add low vram warning
2024-08-19 11:08:01 -07:00
2f1d04759f
avoid some mysteries problems when using lots of python local delegations
2024-08-19 09:47:04 -07:00
0b70b7287c
gradio
2024-08-19 09:12:38 -07:00
584b6c998e
#1294
2024-08-19 09:09:22 -07:00
054a3416f1
revise space logics
2024-08-19 08:06:24 -07:00
96f264ec6a
add a way to save models
2024-08-19 06:30:49 -07:00
4e8ba14dd0
info
2024-08-19 05:13:28 -07:00
d03fc5c2b1
speed up a bit
2024-08-19 05:06:46 -07:00
d38e560e42
Implement some rethinking about LoRA system
...
1. Add an option to allow users to use UNet in fp8/gguf but lora in fp16.
2. All FP16 loras do not need patch. Others will only patch again when lora weight change.
3. FP8 unet + fp16 lora are available (somewhat only available) in Forge now. This also solves some “LoRA too subtle” problems.
4. Significantly speed up all gguf models (in Async mode) by using independent thread (CUDA stream) to compute and dequant at the same time, even when low-bit weights are already on GPU.
5. View “online lora” as a module similar to ControlLoRA so that it is moved to GPU together with model when sampling, achieving significant speedup and perfect low VRAM management simultaneously.
2024-08-19 04:31:59 -07:00
e5f213c21e
upload some GGUF supports
2024-08-19 01:09:50 -07:00
95bc586547
geowizard
2024-08-19 00:27:21 -07:00
00115ae02a
revise space
2024-08-19 00:05:09 -07:00
3bef4e331a
change space path order
2024-08-18 23:55:28 -07:00
deca20551e
pydantic==2.8.2
2024-08-18 22:58:36 -07:00
0024e41107
Update install
2024-08-18 22:55:48 -07:00
631a097d0b
change Florence-2 default to base
2024-08-18 21:31:24 -07:00
ca2db770a9
ic light
2024-08-18 21:16:58 -07:00
4751d6646d
Florence-2
2024-08-18 20:51:44 -07:00
9ec8eabeab
too many models
...
see also https://github.com/lllyasviel/stable-diffusion-webui-forge/issues/1270
2024-08-18 20:25:38 -07:00
1cbd13c85a
Animagine XL 3.1 Official User Interface
2024-08-18 20:05:16 -07:00
4e7c8b5f84
add gitignore
2024-08-18 20:04:51 -07:00
60dfcd0464
revise space
2024-08-18 19:25:39 -07:00
22a19943d2
fix lcm
2024-08-18 19:23:12 -07:00
128a793265
gradio
2024-08-18 03:57:25 -07:00
da72cd6fab
IllusionDiffusion
2024-08-18 03:27:44 -07:00
1e64709d41
gradio
2024-08-18 03:27:24 -07:00
608af2e64c
fix progressbar missing
2024-08-18 02:02:15 -07:00
2292f9a100
Technically Correct PhotoMaker V2
...
that can actually reproduce author results, and be used in serious research and writing academic papers
2024-08-18 01:47:27 -07:00
101b556ee5
revise space logics
2024-08-18 01:44:29 -07:00
72ab92f83e
upload meta files
2024-08-18 00:12:53 -07:00
0ccbac5389
revise space logics
2024-08-18 00:04:02 -07:00
53cd00d125
revise
2024-08-17 23:03:50 -07:00
db5a876d4c
completely solve all LoRA OOMs
2024-08-17 22:43:20 -07:00
93bfd7f85b
invalidate cond cache if distilled CFG changed ( #1240 )
...
* Update processing.py
add distilled_cfg_scale to params that invalidate cond cache
* Update ui.py
distilled CFG and CFG step size 0.1 (from 0.5)
2024-08-17 19:34:11 -07:00
0f266c48bd
make clear_prompt_cache a function
2024-08-17 19:00:13 -07:00
layerdiffusion