chore: format code

examples/common/common.cpp

@@ -1008,7 +1008,7 @@ ArgOptions SDGenerationParams::get_options() {
          &hires_upscaler},
         {"",
          "--extra-sample-args",
-         "extra sampler/scheduler/guidance args, key=value list. CFG supports guidance_schedule; APG supports apg_eta, apg_momentum, apg_norm_threshold, apg_norm_threshold_smoothing; SLG supports slg_uncond; lcm supports noise_clip_std, noise_scale_start, noise_scale_end; flux supports base_shift, max_shift; ltx2 supports max_shift, base_shift, stretch, terminal; euler_ge supports gamma; beta scheduler supports alpha, beta; logit_normal supports mu, std, logsnr_min, logsnr_max, resolution_aware; lms supports lms_divisions",
+         "extra sampler/scheduler/guidance args, key=value list. CFG supports guidance_schedule; APG supports apg_eta, apg_momentum, apg_norm_threshold, apg_norm_threshold_smoothing; SLG supports slg_uncond; lcm supports noise_clip_std, noise_scale_start, noise_scale_end; flux supports base_shift, max_shift; ltx2 supports max_shift, base_shift, stretch, terminal; euler_ge supports gamma; beta scheduler supports alpha, beta; logit_normal supports mu, std, logsnr_min, logsnr_max, resolution_aware; lms supports lms_max_order, lms_shift, lms_divisions",
          (int)',',
          &extra_sample_args},
         {"",
@@ -1555,6 +1555,16 @@ ArgOptions SDGenerationParams::get_options() {
         return 1;
     };
 
+    std::string sample_methods = sample_method_to_str[0];
+    for (int i = 1; i < SAMPLE_METHOD_COUNT; i++) {
+        sample_methods += ", " + std::string(sample_method_to_str[i]);
+    }
+
+    std::string schedulers = scheduler_to_str[0];
+    for (int i = 1; i < SCHEDULER_COUNT; i++) {
+        schedulers += ", " + std::string(scheduler_to_str[i]);
+    }
+
     options.manual_options = {
         {"-s",
          "--seed",
@@ -1562,17 +1572,18 @@ ArgOptions SDGenerationParams::get_options() {
          on_seed_arg},
         {"",
          "--sampling-method",
-         "sampling method, one of [euler, euler_a, heun, dpm2, dpm++2s_a, dpm++2m, dpm++2mv2, dpm++2m_sde, dpm++2m_sde_bt, ipndm, ipndm_v, lcm, ddim_trailing, tcd, res_multistep, res_2s, er_sde, euler_cfg_pp, euler_a_cfg_pp, lms]"
-         "(default: euler for Flux/SD3/Wan, euler_a otherwise)",
+         "sampling method, one of [" + sample_methods + "], "
+                                                        "default: euler for Flux/SD3/Wan, euler_a otherwise",
          on_sample_method_arg},
         {"",
          "--high-noise-sampling-method",
-         "(high noise) sampling method, one of [euler, euler_a, heun, dpm2, dpm++2s_a, dpm++2m, dpm++2mv2, dpm++2m_sde, dpm++2m_sde_bt, ipndm, ipndm_v, lcm, ddim_trailing, tcd, res_multistep, res_2s, er_sde, euler_cfg_pp, euler_a_cfg_pp, lms]"
-         " default: euler for Flux/SD3/Wan, euler_a otherwise",
+         "(high noise) sampling method, one of [" + sample_methods + "], "
+                                                                     "default: euler for Flux/SD3/Wan, euler_a otherwise",
          on_high_noise_sample_method_arg},
         {"",
          "--scheduler",
-         "denoiser sigma scheduler, one of [discrete, karras, exponential, ays, gits, smoothstep, sgm_uniform, simple, kl_optimal, lcm, bong_tangent, ltx2, logit_normal, flux2, flux, beta], alias: normal=discrete, default: model-specific",
+         "denoiser sigma scheduler, one of [" + schedulers + "], "
+                                                             "alias: normal=discrete, default: model-specific",
          on_scheduler_arg},
         {"",
          "--sigmas",

include/stable-diffusion.h

@@ -60,6 +60,8 @@ enum sample_method_t {
     SAMPLE_METHOD_COUNT
 };
 
+extern SD_API const char* sample_method_to_str[];
+
 enum scheduler_t {
     DISCRETE_SCHEDULER,
     KARRAS_SCHEDULER,
@@ -80,6 +82,8 @@ enum scheduler_t {
     SCHEDULER_COUNT
 };
 
+extern SD_API const char* scheduler_to_str[];
+
 enum prediction_t {
     EPS_PRED,
     V_PRED,

scripts/merge_safetensors.py

@@ -23,16 +23,16 @@ from typing import BinaryIO
 # Configuration
 # -----------------------------------------------------------------------------
 
-OUTPUT_PATH = Path(r"..\models\diffusion_models\minimax_h3_ref2va_pruned_bf16.safetensors")
+OUTPUT_PATH = Path(r".minimax_h3_fl2va_pruned_bf16.safetensors")
 
 SOURCE_RULES = [
     {
-        "path": Path(r"..\models\diffusion_models\minimax_h3_ref2va_bf16.safetensors"),
+        "path": Path(r".minimax_h3_fl2va_bf16.safetensors"),
         "include": [r".*"],
         "exclude": [r".*adaln_proj\.linear.*", r"time_embedder.*"],
     },
     {
-        "path": Path(r"..\models\diffusion_models\minimax_h3_ref2va_pruned_int8_convrot.safetensors"),
+        "path": Path(r".minimax_h3_fl2va_pruned_int8_convrot.safetensors"),
         "include": [r"^.*adaln_proj\.linear.*", "adaln_t_table"],
         "exclude": [],
     },

src/core/ggml_extend.hpp

@@ -2456,13 +2456,14 @@ protected:
         GGML_ASSERT(gf != nullptr);
 
         size_t effective_budget = max_graph_vram_bytes;
+        size_t free_clamp       = SIZE_MAX;
         if (stream_layers_enabled && max_graph_vram_bytes > 0 && runtime_backend != nullptr) {
             ggml_backend_dev_t dev = ggml_backend_get_device(runtime_backend);
             if (dev != nullptr && ggml_backend_dev_type(dev) != GGML_BACKEND_DEVICE_TYPE_CPU) {
                 size_t free_vram = 0, total_vram = 0;
                 ggml_backend_dev_memory(dev, &free_vram, &total_vram);
                 constexpr size_t safety_margin = 512ull * 1024 * 1024;
-                size_t free_clamp              = (free_vram > safety_margin) ? (free_vram - safety_margin) : 0;
+                free_clamp                     = (free_vram > safety_margin) ? (free_vram - safety_margin) : 0;
                 if (free_clamp < effective_budget) {
                     LOG_DEBUG("%s clamping streaming budget: actual free VRAM %.2f MB < user cap %.2f MB",
                               get_desc().c_str(),
@@ -2479,7 +2480,9 @@ protected:
                 observed_max_effective_budget_ = effective_budget;
                 budget_increased               = true;
             } else {
-                effective_budget = observed_max_effective_budget_;
+                // Keep the plan cache stable, but never plan above what is free now:
+                // another model or process can take VRAM after the first measurement.
+                effective_budget = std::min(observed_max_effective_budget_, free_clamp);
             }
         }
 

src/core/ggml_graph_cut.cpp

@@ -453,11 +453,12 @@ namespace sd::ggml_graph_cut {
         if (tensor == nullptr || tensor->name[0] == '\0') {
             return false;
         }
-        return std::strncmp(tensor->name, GGML_RUNNER_CUT_PREFIX, std::strlen(GGML_RUNNER_CUT_PREFIX)) == 0;
+        return starts_with(tensor->name, GGML_RUNNER_CUT_PREFIX) &&
+               ends_with(tensor->name, GGML_RUNNER_CUT_SUFFIX);
     }
 
     std::string make_graph_cut_name(const std::string& group, const std::string& output) {
-        return std::string(GGML_RUNNER_CUT_PREFIX) + group + "|" + output;
+        return std::string(GGML_RUNNER_CUT_PREFIX) + group + "|" + output + GGML_RUNNER_CUT_SUFFIX;
     }
 
     void mark_graph_cut(ggml_tensor* tensor, const std::string& group, const std::string& output) {
@@ -603,7 +604,43 @@ namespace sd::ggml_graph_cut {
         GGML_ASSERT(gf != nullptr);
         GGML_ASSERT(graph_ctx_out != nullptr);
 
-        const size_t graph_size = segment.internal_node_indices.size() + segment.input_refs.size() + 8;
+        // Collect leaf inputs and internal nodes, then any tensor they
+        // reference that is not already represented, notably the view_src of a
+        // view-typed input leaf. ggml_gallocr sizes its hash set from
+        // n_nodes + n_leafs (plus a 25% margin that rounds down to zero for a
+        // one-node segment), so every distinct tensor it will hash must be
+        // counted here or a tiny segment overflows the hash set and aborts.
+        std::vector<ggml_tensor*> leaves;
+        std::unordered_set<ggml_tensor*> represented;
+        for (const auto& input : segment.input_refs) {
+            ggml_tensor* current_input = input_tensor(gf, input);
+            if (current_input == nullptr) {
+                continue;
+            }
+            if (represented.insert(current_input).second) {
+                leaves.push_back(current_input);
+            }
+        }
+        for (int node_idx : segment.internal_node_indices) {
+            represented.insert(ggml_graph_node(gf, node_idx));
+        }
+        auto add_reference = [&](ggml_tensor* tensor) {
+            if (tensor != nullptr && represented.insert(tensor).second) {
+                leaves.push_back(tensor);
+            }
+        };
+        for (int node_idx : segment.internal_node_indices) {
+            ggml_tensor* node = ggml_graph_node(gf, node_idx);
+            for (int src_idx = 0; src_idx < GGML_MAX_SRC; ++src_idx) {
+                add_reference(node->src[src_idx]);
+            }
+            add_reference(node->view_src);
+        }
+        for (size_t i = 0; i < leaves.size(); ++i) {
+            add_reference(leaves[i]->view_src);
+        }
+
+        const size_t graph_size = segment.internal_node_indices.size() + leaves.size() + 8;
         ggml_init_params params = {
             /*.mem_size   =*/ggml_graph_overhead_custom(graph_size, false) + 1024,
             /*.mem_buffer =*/nullptr,
@@ -614,13 +651,9 @@ namespace sd::ggml_graph_cut {
         ggml_cgraph* segment_graph = ggml_new_graph_custom(graph_ctx, graph_size, false);
         GGML_ASSERT(segment_graph != nullptr);
 
-        for (const auto& input : segment.input_refs) {
-            ggml_tensor* current_input = input_tensor(gf, input);
-            if (current_input == nullptr) {
-                continue;
-            }
+        for (ggml_tensor* leaf : leaves) {
             GGML_ASSERT(segment_graph->n_leafs < segment_graph->size);
-            segment_graph->leafs[segment_graph->n_leafs++] = current_input;
+            segment_graph->leafs[segment_graph->n_leafs++] = leaf;
         }
 
         for (int output_node_index : segment.output_node_indices) {
@@ -751,7 +784,9 @@ namespace sd::ggml_graph_cut {
 
             plan.has_cuts = true;
             std::string full_name(node->name);
-            std::string payload = full_name.substr(std::strlen(GGML_RUNNER_CUT_PREFIX));
+            size_t prefix_len   = std::strlen(GGML_RUNNER_CUT_PREFIX);
+            size_t suffix_len   = std::strlen(GGML_RUNNER_CUT_SUFFIX);
+            std::string payload = full_name.substr(prefix_len, full_name.size() - prefix_len - suffix_len);
             size_t sep          = payload.find('|');
             std::string group   = sep == std::string::npos ? payload : payload.substr(0, sep);
 

src/core/ggml_graph_cut.h

@@ -68,6 +68,7 @@ namespace sd::ggml_graph_cut {
     };
 
     static constexpr const char* GGML_RUNNER_CUT_PREFIX = "ggml_runner_cut:";
+    static constexpr const char* GGML_RUNNER_CUT_SUFFIX = "|";
 
     struct MaxVramAssignment {
         float default_gib = 0.f;

src/model/vae/tae.hpp

@@ -427,9 +427,9 @@ class TinyVideoDecoder : public UnaryBlock {
     int channels[num_layers + 1] = {256, 128, 64, 64};
     int patch_size               = 1;
     bool is_wide                 = false;
-    
+
 public:
-    int t_upscale                = 1;
+    int t_upscale = 1;
     TinyVideoDecoder(int z_channels = 4, int patch_size = 1, std::vector<bool> time_upscale = {false, true, true}, bool is_wide = false)
         : z_channels(z_channels), patch_size(patch_size), is_wide(is_wide) {
         t_upscale = 1;
@@ -663,7 +663,7 @@ public:
         if (sd_version_is_minimax_h3(version)) {
             return encode_h3(ctx, x);
         }
-        
+
         auto encoder = std::dynamic_pointer_cast<TinyVideoEncoder>(blocks["encoder"]);
 
         int64_t num_frames = x->ne[3];

src/runtime/denoiser.hpp

@@ -2582,27 +2582,49 @@ static sd::Tensor<float> sample_lms(denoise_cb_t model,
                                     sd::Tensor<float> x,
                                     const std::vector<float>& sigmas,
                                     const SamplerExtraArgs& extra_sample_args) {
-    // Linear Multi-Step from https://github.com/crowsonkb/k-diffusion
-
+    // Linear Multi-Step from https://github.com/crowsonkb/k-diffusion,
+    // modified with "history shift" value, which seemingly needs less steps
     int divisions = 1000;
+    int max_order = 4;
+    int shift     = 1;  // 4, 0 - original; 4, 1 - PR #1843; 3, 1 - smoother image
     for (const auto& [key, value] : extra_sample_args) {
         int parsed = 0;
+        if (key == "lms_max_order") {
+            if (!parse_strict_int(value, parsed)) {
+                LOG_WARN("ignoring invalid lms extra sample arg '%s=%s'", key.c_str(), value.c_str());
+                continue;
+            }
+            max_order = std::max(1, parsed);
+            // smaller values make the result softer, closer to Euler
+            // higher values need more steps
+            // values above 12 can produce NaNs, depending on steps and scheduler
+        }
+        if (key == "lms_shift") {
+            if (!parse_strict_int(value, parsed)) {
+                LOG_WARN("ignoring invalid lms extra sample arg '%s=%s'", key.c_str(), value.c_str());
+                continue;
+            }
+            shift = std::max(0, parsed);
+            // for a low number of steps, the value 1 works best
+        }
         if (key == "lms_divisions") {
             if (!parse_strict_int(value, parsed)) {
                 LOG_WARN("ignoring invalid lms extra sample arg '%s=%s'", key.c_str(), value.c_str());
                 continue;
             }
             divisions = parsed;  // std::max(1, parsed);
-            // values above 35M produce noise, can be fixed by double precision
             // values < 1 always produce noise
+            // values above 30M require double precision in the integrator
+            // (they are needless and just slow the integration down, but
+            //  with single precision they softly produce noise
+            //  near the 35M, it can be used for distorted generations)
         }
     }
-    LOG_DEBUG("linear multi-step sampler: integrating using %i division%s", divisions, (divisions == 1) ? "" : "s");
 
     auto linear_multistep_coeff = [=](const int order, const int m, const int j) -> float {
         if (!divisions)
             return sigmas[m + 1] - sigmas[m];  // delta / 0 * 0
-#define LMS_PRECISION float                    // double
+#define LMS_PRECISION float                    // when divisions > 30 millions, the double precision fixes noise
         const LMS_PRECISION a = sigmas[m], dx = (sigmas[m + 1] - a) / divisions, s = sigmas[m - j];
         const LMS_PRECISION b0 = a + 0.5f * dx;  // using Riemann middle integral
         LMS_PRECISION sum      = 0.0f;
@@ -2622,11 +2644,12 @@ static sd::Tensor<float> sample_lms(denoise_cb_t model,
         return sum * dx;
     };
 
-    const int max_order = 4;
-    float lms_coeff[max_order];
+    int steps = static_cast<int>(sigmas.size()) - 1;
+    max_order = std::min(max_order, steps);  // history can not be larger than steps
+    LOG_DEBUG("linear multi-step sampler: lms_max_order = %i, lms_shift = %i, lms_divisions = %i", max_order, shift, divisions);
+    std::vector<float> lms_coeff(max_order);
     std::vector<sd::Tensor<float>> hist = {};
 
-    int steps = static_cast<int>(sigmas.size()) - 1;
     for (int i = 0; i < steps; i++) {
         const float sigma = sigmas[i];
 
@@ -2637,25 +2660,26 @@ static sd::Tensor<float> sample_lms(denoise_cb_t model,
         sd::Tensor<float> denoised = std::move(denoised_opt.pred);
 
         const int order = std::min(max_order, i + 1);
+
         for (int c = 0; c < order; c++)  // computing coefficients
             lms_coeff[c] = linear_multistep_coeff(order, i, c);
 
         sd::Tensor<float> d_cur = (x - denoised) / sigma;
-        switch (order) {
-            case 4:  // derivative + 3 history points
-                x += hist[hist.size() - 2] * lms_coeff[3];
-            case 3:
-                x += hist[hist.size() - 1] * lms_coeff[2];
-            case 2:
-                x += hist.back() * lms_coeff[1];
-            case 1:
-                x += d_cur * lms_coeff[0];
+        x += d_cur * lms_coeff[0];
+        if (max_order > 1) {  // if max_order == 1, the history is not used (order always < 2)
+            int hist_size_p1 = hist.size() + 1;
+            if (i) {  // history does not exist at 1st step
+                int hist_max = hist.size() - 1;
+                for (int c = 2; c <= order; c++)
+                    x += hist[std::min(hist_max, hist_size_p1 - c + shift)] * lms_coeff[c - 1];
+                // max_order == 4  =>  hist[] index = 2, 1, 0
+                // shift == 1      =>  hist[] index = 2, 2, 1
+            }
+            if (hist_size_p1 == max_order) {
+                hist.erase(hist.begin());
+            }
+            hist.push_back(std::move(d_cur));
         }
-
-        if (hist.size() == static_cast<size_t>(max_order - 1)) {
-            hist.erase(hist.begin());
-        }
-        hist.push_back(std::move(d_cur));
     }
     return x;
 }

src/stable-diffusion.cpp

@@ -150,6 +150,9 @@ const char* sampling_methods_str[] = {
     "LMS",
 };
 
+static_assert(SAMPLE_METHOD_COUNT == sizeof(sampling_methods_str) / sizeof(sampling_methods_str[0]),
+              "\nnumber of elements in sampling_methods_str[] != SAMPLE_METHOD_COUNT");
+
 /*================================================== Helper Functions ================================================*/
 
 static bool sd_version_supports_ref_latent_img_cfg(SDVersion version) {
@@ -2312,7 +2315,7 @@ public:
                     return;
                 }
             } else if (channels == 24) {
-                if(sd_version_is_minimax_h3(version)){
+                if (sd_version_is_minimax_h3(version)) {
                     latent_rgb_proj = minimax_latent_rgb_proj;
                     latent_rgb_bias = minimax_latent_rgb_bias;
                 } else {
@@ -3306,6 +3309,9 @@ const char* sample_method_to_str[] = {
     "lms",
 };
 
+static_assert(SAMPLE_METHOD_COUNT == sizeof(sample_method_to_str) / sizeof(sample_method_to_str[0]),
+              "\nnumber of elements in sample_method_to_str[] != SAMPLE_METHOD_COUNT");
+
 const char* sd_sample_method_name(enum sample_method_t sample_method) {
     if (sample_method < SAMPLE_METHOD_COUNT) {
         return sample_method_to_str[sample_method];
@@ -3341,6 +3347,9 @@ const char* scheduler_to_str[] = {
     "beta",
 };
 
+static_assert(SCHEDULER_COUNT == sizeof(scheduler_to_str) / sizeof(scheduler_to_str[0]),
+              "\nnumber of elements in scheduler_to_str[] != SCHEDULER_COUNT");
+
 const char* sd_scheduler_name(enum scheduler_t scheduler) {
     if (scheduler < SCHEDULER_COUNT) {
         return scheduler_to_str[scheduler];