DarthAffe/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-03-24 02:08:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: update sd-cli/sd-server docs

Browse Source
This commit is contained in:
leejet 2026-03-04 00:41:17 +08:00
parent ba35dd734e
commit aaa8a51bd8
2 changed files with 28 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
examples/cli/README.md
View File

@ -4,11 +4,12 @@
usage: ./bin/sd-cli [options] usage: ./bin/sd-cli [options]
CLI Options: CLI Options:
-o, --output <string> path to write result image to. you can use printf-style %d format specifiers for image sequences (default: ./output.png) (eg. output_%03d.png) -o, --output <string> path to write result image to. you can use printf-style %d format specifiers for image sequences (default:
--output-begin-idx <int> starting index for output image sequence, must be non-negative (default 0 if specified %d in output path, 1 otherwise) ./output.png) (eg. output_%03d.png)
--preview-path <string> path to write preview image to (default: ./preview.png) --preview-path <string> path to write preview image to (default: ./preview.png)
--preview-interval <int> interval in denoising steps between consecutive updates of the image preview file (default is 1, meaning updating at --preview-interval <int> interval in denoising steps between consecutive updates of the image preview file (default is 1, meaning updating at
every step) every step)
--output-begin-idx <int> starting index for output image sequence, must be non-negative (default 0 if specified %d in output path, 1 otherwise)
--canny apply canny preprocessor (edge detection) --canny apply canny preprocessor (edge detection)
--convert-name convert tensor name (for convert mode) --convert-name convert tensor name (for convert mode)
-v, --verbose print extra info -v, --verbose print extra info
@ -59,6 +60,7 @@ Context Options:
--circularx enable circular RoPE wrapping on x-axis (width) only --circularx enable circular RoPE wrapping on x-axis (width) only
--circulary enable circular RoPE wrapping on y-axis (height) only --circulary enable circular RoPE wrapping on y-axis (height) only
--chroma-disable-dit-mask disable dit mask for chroma --chroma-disable-dit-mask disable dit mask for chroma
--qwen-image-zero-cond-t enable zero_cond_t for qwen image
--chroma-enable-t5-mask enable t5 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 --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
type of the weight file type of the weight file
@ -107,7 +109,7 @@ Generation Options:
medium medium
--skip-layer-start <float> SLG enabling point (default: 0.01) --skip-layer-start <float> SLG enabling point (default: 0.01)
--skip-layer-end <float> SLG disabling point (default: 0.2) --skip-layer-end <float> SLG disabling point (default: 0.2)
--eta <float> eta in DDIM, only for DDIM/TCD/res_multistep/res_2s (default: 0) --eta <float> eta in DDIM, only for DDIM and TCD (default: 0)
--flow-shift <float> shift value for Flow models like SD3.x or WAN (default: auto) --flow-shift <float> shift value for Flow models like SD3.x or WAN (default: auto)
--high-noise-cfg-scale <float> (high noise) unconditional guidance scale: (default: 7.0) --high-noise-cfg-scale <float> (high noise) unconditional guidance scale: (default: 7.0)
--high-noise-img-cfg-scale <float> (high noise) image guidance scale for inpaint or instruct-pix2pix models (default: same as --cfg-scale) --high-noise-img-cfg-scale <float> (high noise) image guidance scale for inpaint or instruct-pix2pix models (default: same as --cfg-scale)
@ -115,7 +117,7 @@ Generation Options:
--high-noise-slg-scale <float> (high noise) skip layer guidance (SLG) scale, only for DiT models: (default: 0) --high-noise-slg-scale <float> (high noise) skip layer guidance (SLG) scale, only for DiT models: (default: 0)
--high-noise-skip-layer-start <float> (high noise) SLG enabling point (default: 0.01) --high-noise-skip-layer-start <float> (high noise) SLG enabling point (default: 0.01)
--high-noise-skip-layer-end <float> (high noise) SLG disabling point (default: 0.2) --high-noise-skip-layer-end <float> (high noise) SLG disabling point (default: 0.2)
--high-noise-eta <float> (high noise) eta in DDIM, only for DDIM/TCD/res_multistep/res_2s (default: 0) --high-noise-eta <float> (high noise) eta in DDIM, only for DDIM and TCD (default: 0)
--strength <float> strength for noising/unnoising (default: 0.75) --strength <float> strength for noising/unnoising (default: 0.75)
--pm-style-strength <float> --pm-style-strength <float>
--control-strength <float> strength to apply Control Net (default: 0.9). 1.0 corresponds to full destruction of information in init image --control-strength <float> strength to apply Control Net (default: 0.9). 1.0 corresponds to full destruction of information in init image
@ -124,10 +126,12 @@ Generation Options:
--increase-ref-index automatically increase the indices of references images based on the order they are listed (starting with 1). --increase-ref-index automatically increase the indices of references images based on the order they are listed (starting with 1).
--disable-auto-resize-ref-image disable auto resize of ref images --disable-auto-resize-ref-image disable auto resize of ref images
-s, --seed RNG seed (default: 42, use random seed for < 0) -s, --seed RNG seed (default: 42, use random seed for < 0)
--sampling-method sampling method, one of [euler, euler_a, heun, dpm2, dpm++2s_a, dpm++2m, dpm++2mv2, ipndm, ipndm_v, lcm, ddim_trailing, tcd, --sampling-method sampling method, one of [euler, euler_a, heun, dpm2, dpm++2s_a, dpm++2m, dpm++2mv2, ipndm, ipndm_v, lcm, ddim_trailing,
res_multistep, res_2s] (default: euler for Flux/SD3/Wan, euler_a otherwise) tcd, res_multistep, res_2s] (default: euler for Flux/SD3/Wan, euler_a
--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, otherwise)
tcd, res_multistep, res_2s] 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, res_multistep, res_2s] default: euler for Flux/SD3/Wan,
euler_a otherwise
--scheduler denoiser sigma scheduler, one of [discrete, karras, exponential, ays, gits, smoothstep, sgm_uniform, simple, --scheduler denoiser sigma scheduler, one of [discrete, karras, exponential, ays, gits, smoothstep, sgm_uniform, simple,
kl_optimal, lcm, bong_tangent], default: discrete kl_optimal, lcm, bong_tangent], default: discrete
--sigmas custom sigma values for the sampler, comma-separated (e.g., "14.61,7.8,3.5,0.0"). --sigmas custom sigma values for the sampler, comma-separated (e.g., "14.61,7.8,3.5,0.0").

29
examples/server/README.md
View File

@ -4,12 +4,12 @@
usage: ./bin/sd-server [options] usage: ./bin/sd-server [options]
Svr Options: Svr Options:
-l, --listen-ip <string> server listen ip (default: 127.0.0.1) -l, --listen-ip <string> server listen ip (default: 127.0.0.1)
--listen-port <int> server listen port (default: 1234) --serve-html-path <string> path to HTML file to serve at root (optional)
--serve-html-path <string> path to HTML file to serve at root (optional) --listen-port <int> server listen port (default: 1234)
-v, --verbose print extra info -v, --verbose print extra info
--color colors the logging tags according to level --color colors the logging tags according to level
-h, --help show this help message and exit -h, --help show this help message and exit
Context Options: Context Options:
-m, --model <string> path to full model -m, --model <string> path to full model
@ -39,10 +39,10 @@ Context Options:
--vae-tiling process vae in tiles to reduce memory usage --vae-tiling process vae in tiles to reduce memory usage
--force-sdxl-vae-conv-scale force use of conv scale on sdxl vae --force-sdxl-vae-conv-scale force use of conv scale on sdxl vae
--offload-to-cpu place the weights in RAM to save VRAM, and automatically load them into VRAM when needed --offload-to-cpu place the weights in RAM to save VRAM, and automatically load them into VRAM when needed
--mmap whether to memory-map model
--control-net-cpu keep controlnet in cpu (for low vram) --control-net-cpu keep controlnet in cpu (for low vram)
--clip-on-cpu keep clip in cpu (for low vram) --clip-on-cpu keep clip in cpu (for low vram)
--vae-on-cpu keep vae in cpu (for low vram) --vae-on-cpu keep vae in cpu (for low vram)
--mmap whether to memory-map model
--fa use flash attention --fa use flash attention
--diffusion-fa use flash attention in the diffusion model only --diffusion-fa use flash attention in the diffusion model only
--diffusion-conv-direct use ggml_conv2d_direct in the diffusion model --diffusion-conv-direct use ggml_conv2d_direct in the diffusion model
@ -51,6 +51,7 @@ Context Options:
--circularx enable circular RoPE wrapping on x-axis (width) only --circularx enable circular RoPE wrapping on x-axis (width) only
--circulary enable circular RoPE wrapping on y-axis (height) only --circulary enable circular RoPE wrapping on y-axis (height) only
--chroma-disable-dit-mask disable dit mask for chroma --chroma-disable-dit-mask disable dit mask for chroma
--qwen-image-zero-cond-t enable zero_cond_t for qwen image
--chroma-enable-t5-mask enable t5 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 --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
type of the weight file type of the weight file
@ -99,7 +100,7 @@ Default Generation Options:
medium medium
--skip-layer-start <float> SLG enabling point (default: 0.01) --skip-layer-start <float> SLG enabling point (default: 0.01)
--skip-layer-end <float> SLG disabling point (default: 0.2) --skip-layer-end <float> SLG disabling point (default: 0.2)
--eta <float> eta in DDIM, only for DDIM/TCD/res_multistep/res_2s (default: 0) --eta <float> eta in DDIM, only for DDIM and TCD (default: 0)
--flow-shift <float> shift value for Flow models like SD3.x or WAN (default: auto) --flow-shift <float> shift value for Flow models like SD3.x or WAN (default: auto)
--high-noise-cfg-scale <float> (high noise) unconditional guidance scale: (default: 7.0) --high-noise-cfg-scale <float> (high noise) unconditional guidance scale: (default: 7.0)
--high-noise-img-cfg-scale <float> (high noise) image guidance scale for inpaint or instruct-pix2pix models (default: same as --cfg-scale) --high-noise-img-cfg-scale <float> (high noise) image guidance scale for inpaint or instruct-pix2pix models (default: same as --cfg-scale)
@ -107,7 +108,7 @@ Default Generation Options:
--high-noise-slg-scale <float> (high noise) skip layer guidance (SLG) scale, only for DiT models: (default: 0) --high-noise-slg-scale <float> (high noise) skip layer guidance (SLG) scale, only for DiT models: (default: 0)
--high-noise-skip-layer-start <float> (high noise) SLG enabling point (default: 0.01) --high-noise-skip-layer-start <float> (high noise) SLG enabling point (default: 0.01)
--high-noise-skip-layer-end <float> (high noise) SLG disabling point (default: 0.2) --high-noise-skip-layer-end <float> (high noise) SLG disabling point (default: 0.2)
--high-noise-eta <float> (high noise) eta in DDIM, only for DDIM/TCD/res_multistep/res_2s (default: 0) --high-noise-eta <float> (high noise) eta in DDIM, only for DDIM and TCD (default: 0)
--strength <float> strength for noising/unnoising (default: 0.75) --strength <float> strength for noising/unnoising (default: 0.75)
--pm-style-strength <float> --pm-style-strength <float>
--control-strength <float> strength to apply Control Net (default: 0.9). 1.0 corresponds to full destruction of information in init image --control-strength <float> strength to apply Control Net (default: 0.9). 1.0 corresponds to full destruction of information in init image
@ -116,10 +117,12 @@ Default Generation Options:
--increase-ref-index automatically increase the indices of references images based on the order they are listed (starting with 1). --increase-ref-index automatically increase the indices of references images based on the order they are listed (starting with 1).
--disable-auto-resize-ref-image disable auto resize of ref images --disable-auto-resize-ref-image disable auto resize of ref images
-s, --seed RNG seed (default: 42, use random seed for < 0) -s, --seed RNG seed (default: 42, use random seed for < 0)
--sampling-method sampling method, one of [euler, euler_a, heun, dpm2, dpm++2s_a, dpm++2m, dpm++2mv2, ipndm, ipndm_v, lcm, ddim_trailing, tcd, --sampling-method sampling method, one of [euler, euler_a, heun, dpm2, dpm++2s_a, dpm++2m, dpm++2mv2, ipndm, ipndm_v, lcm, ddim_trailing,
res_multistep, res_2s] (default: euler for Flux/SD3/Wan, euler_a otherwise) tcd, res_multistep, res_2s] (default: euler for Flux/SD3/Wan, euler_a
--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, otherwise)
tcd, res_multistep, res_2s] 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, res_multistep, res_2s] default: euler for Flux/SD3/Wan,
euler_a otherwise
--scheduler denoiser sigma scheduler, one of [discrete, karras, exponential, ays, gits, smoothstep, sgm_uniform, simple, --scheduler denoiser sigma scheduler, one of [discrete, karras, exponential, ays, gits, smoothstep, sgm_uniform, simple,
kl_optimal, lcm, bong_tangent], default: discrete kl_optimal, lcm, bong_tangent], default: discrete
--sigmas custom sigma values for the sampler, comma-separated (e.g., "14.61,7.8,3.5,0.0"). --sigmas custom sigma values for the sampler, comma-separated (e.g., "14.61,7.8,3.5,0.0").