DarthAffe/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-01-02 10:43:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: update README.md

Browse Source
This commit is contained in:
leejet 2025-12-22 23:58:28 +08:00
parent 298b11069f
commit 98916e8256
3 changed files with 30 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -143,6 +143,7 @@ If you want to improve performance or reduce VRAM/RAM usage, please refer to [pe
- [Using TAESD to faster decoding](./docs/taesd.md)
- [Docker](./docs/docker.md)
- [Quantization and GGUF](./docs/quantization_and_gguf.md)
- [Inference acceleration via caching](./docs/caching.md)
## Bindings

19
examples/cli/README.md
View File

@ -53,6 +53,9 @@ Context Options:
--diffusion-fa use flash attention in the diffusion model
--diffusion-conv-direct use ggml_conv2d_direct in the diffusion model
--vae-conv-direct use ggml_conv2d_direct in the vae model
--circular enable circular padding for convolutions
--circularx enable circular RoPE wrapping on x-axis (width) only
--circulary enable circular RoPE wrapping on y-axis (height) only
--chroma-disable-dit-mask disable dit mask for chroma
--chroma-enable-t5-mask enable t5 mask for chroma
--type weight type (examples: f32, f16, q4_0, q4_1, q5_0, q5_1, q8_0, q2_K, q3_K, q4_K). If not specified, the default is the
@ -94,6 +97,7 @@ Generation Options:
--timestep-shift <int> shift timestep for NitroFusion models (default: 0). recommended N for NitroSD-Realism around 250 and 500 for
NitroSD-Vibrant
--upscale-repeats <int> Run the ESRGAN upscaler this many times (default: 1)
--upscale-tile-size <int> tile size for ESRGAN upscaling (default: 128)
--cfg-scale <float> unconditional guidance scale: (default: 7.0)
--img-cfg-scale <float> image guidance scale for inpaint or instruct-pix2pix models: (default: same as --cfg-scale)
--guidance <float> distilled guidance scale for models with guidance input (default: 3.5)
@ -121,18 +125,21 @@ Generation Options:
tcd] (default: euler for Flux/SD3/Wan, euler_a otherwise)
--high-noise-sampling-method (high noise) sampling method, one of [euler, euler_a, heun, dpm2, dpm++2s_a, dpm++2m, dpm++2mv2, ipndm, ipndm_v, lcm,
ddim_trailing, tcd] default: euler for Flux/SD3/Wan, euler_a otherwise
--scheduler denoiser sigma scheduler, one of [discrete, karras, exponential, ays, gits, smoothstep, sgm_uniform, simple, kl_optimal, lcm],
default: discrete
--scheduler denoiser sigma scheduler, one of [discrete, karras, exponential, ays, gits, smoothstep, sgm_uniform, simple,
kl_optimal, lcm], default: discrete
--sigmas custom sigma values for the sampler, comma-separated (e.g., "14.61,7.8,3.5,0.0").
--skip-layers layers to skip for SLG steps (default: [7,8,9])
--high-noise-skip-layers (high noise) layers to skip for SLG steps (default: [7,8,9])
-r, --ref-image reference image for Flux Kontext models (can be used multiple times)
--cache-mode caching method: 'easycache' (DiT), 'ucache' (UNET), 'dbcache'/'taylorseer'/'cache-dit' (DiT block-level)
--cache-option named cache params (key=value format, comma-separated):
- easycache/ucache: threshold=,start=,end=,decay=,relative=,reset=
- dbcache/taylorseer/cache-dit: Fn=,Bn=,threshold=,warmup=
Examples: "threshold=0.25" or "threshold=1.5,reset=0"
- easycache/ucache:
threshold=,start=,end=,decay=,relative=,reset=
- dbcache/taylorseer/cache-dit:
Fn=,Bn=,threshold=,warmup=
Examples: "threshold=0.25" or
"threshold=1.5,reset=0"
--cache-preset cache-dit preset: 'slow'/'s', 'medium'/'m', 'fast'/'f', 'ultra'/'u'
--scm-mask SCM steps mask: comma-separated 0/1 (1=compute, 0=can cache)
--scm-mask SCM steps mask for cache-dit: comma-separated 0/1 (e.g., "1,1,1,0,0,1,0,0,1,0") - 1=compute, 0=can cache
--scm-policy SCM policy: 'dynamic' (default) or 'static'
```

19
examples/server/README.md
View File

@ -45,6 +45,9 @@ Context Options:
--diffusion-fa use flash attention in the diffusion model
--diffusion-conv-direct use ggml_conv2d_direct in the diffusion model
--vae-conv-direct use ggml_conv2d_direct in the vae model
--circular enable circular padding for convolutions
--circularx enable circular RoPE wrapping on x-axis (width) only
--circulary enable circular RoPE wrapping on y-axis (height) only
--chroma-disable-dit-mask disable dit mask for chroma
--chroma-enable-t5-mask enable t5 mask for chroma
--type weight type (examples: f32, f16, q4_0, q4_1, q5_0, q5_1, q8_0, q2_K, q3_K, q4_K). If not specified, the default is the
@ -114,11 +117,21 @@ Default Generation Options:
tcd] (default: euler for Flux/SD3/Wan, euler_a otherwise)
--high-noise-sampling-method (high noise) sampling method, one of [euler, euler_a, heun, dpm2, dpm++2s_a, dpm++2m, dpm++2mv2, ipndm, ipndm_v, lcm,
ddim_trailing, tcd] default: euler for Flux/SD3/Wan, euler_a otherwise
--scheduler denoiser sigma scheduler, one of [discrete, karras, exponential, ays, gits, smoothstep, sgm_uniform, simple, kl_optimal, lcm],
default: discrete
--scheduler denoiser sigma scheduler, one of [discrete, karras, exponential, ays, gits, smoothstep, sgm_uniform, simple,
kl_optimal, lcm], default: discrete
--sigmas custom sigma values for the sampler, comma-separated (e.g., "14.61,7.8,3.5,0.0").
--skip-layers layers to skip for SLG steps (default: [7,8,9])
--high-noise-skip-layers (high noise) layers to skip for SLG steps (default: [7,8,9])
-r, --ref-image reference image for Flux Kontext models (can be used multiple times)
--easycache enable EasyCache for DiT models with optional "threshold,start_percent,end_percent" (default: 0.2,0.15,0.95)
--cache-mode caching method: 'easycache' (DiT), 'ucache' (UNET), 'dbcache'/'taylorseer'/'cache-dit' (DiT block-level)
--cache-option named cache params (key=value format, comma-separated):
- easycache/ucache:
threshold=,start=,end=,decay=,relative=,reset=
- dbcache/taylorseer/cache-dit:
Fn=,Bn=,threshold=,warmup=
Examples: "threshold=0.25" or
"threshold=1.5,reset=0"
--cache-preset cache-dit preset: 'slow'/'s', 'medium'/'m', 'fast'/'f', 'ultra'/'u'
--scm-mask SCM steps mask for cache-dit: comma-separated 0/1 (e.g., "1,1,1,0,0,1,0,0,1,0") - 1=compute, 0=can cache
--scm-policy SCM policy: 'dynamic' (default) or 'static'
```