leejet
ed374983f3
fix: set eps of ggml_norm(LayerNorm) to 1e-5
2023-10-27 00:50:23 +08:00
leejet
fbd18e1059
fix: avoid stack overflow on MSVC
2023-10-23 21:10:46 +08:00
leejet
69e54ace14
sync: update ggml
2023-10-22 14:11:06 +08:00
Urs Ganse
3a25179d52
feat: add DPM2 and DPM++(2s) a samplers ( #56 )
...
* Add DPM2 sampler.
* Add DPM++ (2s) a sampler.
* Update README.md with added samplers
---------
Co-authored-by: leejet <leejet714@gmail.com>
2023-09-12 23:02:09 +08:00
Urs Ganse
968fbf02aa
feat: add option to switch the sigma schedule ( #51 )
...
Concretely, this allows switching to the "Karras" schedule from the
Karras et al 2022 paper, equivalent to the samplers marked as "Karras"
in the AUTOMATIC1111 WebUI. This choice is in principle orthogonal to
the sampler choice and can be given independently.
2023-09-09 00:02:07 +08:00
Urs Ganse
b6899e8fc2
feat: add Euler, Heun and DPM++ (2M) samplers ( #50 )
...
* Add Euler sampler
* Add Heun sampler
* Add DPM++ (2M) sampler
* Add modified DPM++ (2M) "v2" sampler.
This was proposed in a issue discussion of the stable diffusion webui,
at https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/8457
and apparently works around overstepping of the DPM++ (2M) method with
small step counts.
The parameter is called dpmpp2mv2 here.
* match code style
---------
Co-authored-by: Urs Ganse <urs@nerd2nerd.org>
Co-authored-by: leejet <leejet714@gmail.com>
2023-09-08 23:47:28 +08:00
leejet
34a118d407
fix: avoid coredump when steps == 1
2023-09-04 21:44:38 +08:00
leejet
f6ff06fcb7
fix: avoid coredump when generating large image
2023-09-04 21:37:46 +08:00
leejet
b247581782
fix: insufficient memory error on macOS
2023-09-04 03:50:42 +08:00
leejet
bb3f19cb40
fix: increase ctx_size
2023-09-04 03:45:43 +08:00
leejet
7620b920c8
use new graph api to avoid stack overflow on msvc
2023-09-03 22:56:33 +08:00
leejet
3ffffa6929
fix: do not check weights of open clip last layer
2023-09-03 21:10:08 +08:00
leejet
45842865ff
fix: seed should be 64 bit
2023-09-03 20:08:22 +08:00
leejet
e5a7aec252
feat: add CUDA RNG
2023-09-03 19:24:07 +08:00
leejet
31e77e1573
feat: add SD2.x support ( #40 )
2023-09-03 16:00:33 +08:00
leejet
c542a77a3f
fix: correct the handling of weight loading
2023-08-30 21:44:06 +08:00
Derek Anderson
1b5a868296
fix: flushes after printf ( #38 )
2023-08-30 20:47:25 +08:00
leejet
c8f85a4e30
sync: update ggml
2023-08-27 14:35:26 +08:00
leejet
d765b95ed1
perf: make ggml_conv_2d faster
2023-08-26 17:08:59 +08:00
Tim Miller
a22722631a
fix: fix regex for macOS/Clang support ( #16 )
...
---------
Co-authored-by: leejet <leejet714@gmail.com>
2023-08-21 21:55:00 +08:00
leejet
17095dddea
feat: add token weighting support ( #13 )
2023-08-20 20:28:36 +08:00
leejet
8f34dd7cc7
perf: free unused params immediately to reduce memory usage
2023-08-17 00:55:36 +08:00
leejet
7aeb2fab63
perf: sync ggml
2023-08-16 22:20:00 +08:00
leejet
58735a2813
feat: add img2img mode ( #5 )
2023-08-16 01:48:07 +08:00
leejet
228e94b924
fix: include extra header files to prevent compile errors on some platforms
2023-08-13 21:44:40 +08:00
leejet
3aca342e60
Initial commit
2023-08-13 16:00:22 +08:00
