DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 03:24:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add flux2 support (#1016)

Browse Source 
* add flux2 support

* rename qwenvl to llm

* add Flux2FlowDenoiser

* update docs
This commit is contained in:
leejet authored and GitHub committed 2025-11-30 11:32:56 +08:00
1 parent 20345888a3
commit 52b67c538b
21 files changed
+489706 -576
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

examples/cli/README.md
+8 -8
View File
@@ -9,8 +9,10 @@ Options:
--clip_g <string> path to the clip-g text encoder
--clip_vision <string> path to the clip-vision encoder
--t5xxl <string> path to the t5xxl text encoder
--qwen2vl <string> path to the qwen2vl text encoder
--qwen2vl_vision <string> path to the qwen2vl vit
--llm <string> path to the llm text encoder. For example: (qwenvl2.5 for qwen-image, mistral-small3.2 for flux2, ...)
--llm_vision <string> path to the llm vit
--qwen2vl <string> alias of --llm. Deprecated.
--qwen2vl_vision <string> alias of --llm_vision. Deprecated.
--diffusion-model <string> path to the standalone diffusion model
--high-noise-diffusion-model <string> path to the standalone high noise diffusion model
--vae <string> path to standalone vae model
@@ -33,7 +35,6 @@ Options:
-p, --prompt <string> the prompt to render
-n, --negative-prompt <string> the negative prompt (default: "")
--preview-path <string> path to write preview image to (default: ./preview.png)
--easycache <string> enable EasyCache for DiT models, accepts optional "threshold,start_percent,end_percent" values (defaults to 0.2,0.15,0.95)
--upscale-model <string> path to esrgan model.
-t, --threads <int> number of threads to use during computation (default: -1). If threads <= 0, then threads will be set to the number of
CPU physical cores
@@ -100,20 +101,18 @@ Options:
-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] (default: euler for Flux/SD3/Wan, euler_a otherwise)
--prediction prediction type override, one of [eps, v, edm_v, sd3_flow, flux_flow]
--prediction prediction type override, one of [eps, v, edm_v, sd3_flow, flux_flow, flux2_flow]
--lora-apply-mode the way to apply LoRA, one of [auto, immediately, at_runtime], default is auto. In auto mode, if the model weights
contain any quantized parameters, the at_runtime mode will be used; otherwise,
immediately will be used.The immediately mode may have precision and
compatibility issues with quantized parameters, but it usually offers faster inference
speed and, in some cases, lower memory usage. The at_runtime mode, on the other
hand, is exactly the opposite.
speed and, in some cases, lower memory usage. The at_runtime mode, on the
other hand, is exactly the opposite.
--scheduler denoiser sigma scheduler, one of [discrete, karras, exponential, ays, gits, smoothstep, sgm_uniform, simple, lcm],
default: discrete
--skip-layers layers to skip for SLG steps (default: [7,8,9])
--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
--high-noise-scheduler (high noise) denoiser sigma scheduler, one of [discrete, karras, exponential, ays, gits, smoothstep, sgm_uniform,
simple], default: discrete
--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)
-h, --help show this help message and exit
@@ -121,4 +120,5 @@ Options:
--vae-relative-tile-size relative tile size for vae tiling, format [X]x[Y], in fraction of image size if < 1, in number of tiles per dim if >=1
(overrides --vae-tile-size)
--preview preview method. must be one of the following [none, proj, tae, vae] (default is none)
--easycache enable EasyCache for DiT models with optional "threshold,start_percent,end_percent" (default: 0.2,0.15,0.95)
```
examples/cli/main.cpp
+21 -13
View File
@@ -70,8 +70,8 @@ struct SDParams {
std::string clip_g_path;
std::string clip_vision_path;
std::string t5xxl_path;
std::string qwen2vl_path;
std::string qwen2vl_vision_path;
std::string llm_path;
std::string llm_vision_path;
std::string diffusion_model_path;
std::string high_noise_diffusion_model_path;
std::string vae_path;
@@ -174,8 +174,8 @@ void print_params(SDParams params) {
printf(" clip_g_path: %s\n", params.clip_g_path.c_str());
printf(" clip_vision_path: %s\n", params.clip_vision_path.c_str());
printf(" t5xxl_path: %s\n", params.t5xxl_path.c_str());
printf(" qwen2vl_path: %s\n", params.qwen2vl_path.c_str());
printf(" qwen2vl_vision_path: %s\n", params.qwen2vl_vision_path.c_str());
printf(" llm_path: %s\n", params.llm_path.c_str());
printf(" llm_vision_path: %s\n", params.llm_vision_path.c_str());
printf(" diffusion_model_path: %s\n", params.diffusion_model_path.c_str());
printf(" high_noise_diffusion_model_path: %s\n", params.high_noise_diffusion_model_path.c_str());
printf(" vae_path: %s\n", params.vae_path.c_str());
@@ -532,14 +532,22 @@ void parse_args(int argc, const char** argv, SDParams& params) {
"--t5xxl",
"path to the t5xxl text encoder",
&params.t5xxl_path},
{"",
"--llm",
"path to the llm text encoder. For example: (qwenvl2.5 for qwen-image, mistral-small3.2 for flux2, ...)",
&params.llm_path},
{"",
"--llm_vision",
"path to the llm vit",
&params.llm_vision_path},
{"",
"--qwen2vl",
"path to the qwen2vl text encoder",
&params.qwen2vl_path},
"alias of --llm. Deprecated.",
&params.llm_path},
{"",
"--qwen2vl_vision",
"path to the qwen2vl vit",
&params.qwen2vl_vision_path},
"alias of --llm_vision. Deprecated.",
&params.llm_vision_path},
{"",
"--diffusion-model",
"path to the standalone diffusion model",
@@ -1185,7 +1193,7 @@ void parse_args(int argc, const char** argv, SDParams& params) {
on_sample_method_arg},
{"",
"--prediction",
"prediction type override, one of [eps, v, edm_v, sd3_flow, flux_flow]",
"prediction type override, one of [eps, v, edm_v, sd3_flow, flux_flow, flux2_flow]",
on_prediction_arg},
{"",
"--lora-apply-mode",
@@ -1230,7 +1238,7 @@ void parse_args(int argc, const char** argv, SDParams& params) {
on_relative_tile_size_arg},
{"",
"--preview",
std::string("preview method. must be one of the following [") + previews_str[0] + ", " + previews_str[1] + ", " + previews_str[2] + ", " + previews_str[3] + "] (default is " + previews_str[PREVIEW_NONE] + ")\n",
std::string("preview method. must be one of the following [") + previews_str[0] + ", " + previews_str[1] + ", " + previews_str[2] + ", " + previews_str[3] + "] (default is " + previews_str[PREVIEW_NONE] + ")",
on_preview_arg},
{"",
"--easycache",
@@ -1428,7 +1436,7 @@ std::string get_image_params(SDParams params, int64_t seed) {
parameter_string += " " + std::string(sd_scheduler_name(params.sample_params.scheduler));
}
parameter_string += ", ";
for (const auto& te : {params.clip_l_path, params.clip_g_path, params.t5xxl_path, params.qwen2vl_path, params.qwen2vl_vision_path}) {
for (const auto& te : {params.clip_l_path, params.clip_g_path, params.t5xxl_path, params.llm_path, params.llm_vision_path}) {
if (!te.empty()) {
parameter_string += "TE: " + sd_basename(te) + ", ";
}
@@ -1845,8 +1853,8 @@ int main(int argc, const char* argv[]) {
params.clip_g_path.c_str(),
params.clip_vision_path.c_str(),
params.t5xxl_path.c_str(),
params.qwen2vl_path.c_str(),
params.qwen2vl_vision_path.c_str(),
params.llm_path.c_str(),
params.llm_vision_path.c_str(),
params.diffusion_model_path.c_str(),
params.high_noise_diffusion_model_path.c_str(),
params.vae_path.c_str(),