From 98916e825686f8952126b2c54e1c4216eb418dc5 Mon Sep 17 00:00:00 2001 From: leejet Date: Mon, 22 Dec 2025 23:58:28 +0800 Subject: [PATCH] docs: update README.md --- README.md | 1 + examples/cli/README.md | 19 +++++++++++++------ examples/server/README.md | 19 ++++++++++++++++--- 3 files changed, 30 insertions(+), 9 deletions(-) diff --git a/README.md b/README.md index aa29f84..3c66be9 100644 --- a/README.md +++ b/README.md @@ -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 diff --git a/examples/cli/README.md b/examples/cli/README.md index 0617a46..568f29d 100644 --- a/examples/cli/README.md +++ b/examples/cli/README.md @@ -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 shift timestep for NitroFusion models (default: 0). recommended N for NitroSD-Realism around 250 and 500 for NitroSD-Vibrant --upscale-repeats Run the ESRGAN upscaler this many times (default: 1) + --upscale-tile-size tile size for ESRGAN upscaling (default: 128) --cfg-scale unconditional guidance scale: (default: 7.0) --img-cfg-scale image guidance scale for inpaint or instruct-pix2pix models: (default: same as --cfg-scale) --guidance 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' ``` diff --git a/examples/server/README.md b/examples/server/README.md index ae10496..89d8560 100644 --- a/examples/server/README.md +++ b/examples/server/README.md @@ -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' ```