From f215b1655d204bf32e9cdc4c4fb0d5e110f1b429 Mon Sep 17 00:00:00 2001
From: Pedro Cuenca <pedro@huggingface.co>
Date: Tue, 4 Aug 2026 17:24:42 +0200
Subject: [PATCH] Pre-processing

---
 tools/mtmd/mtmd-image.cpp | 62 +++++++++++++++++++++++++++++++++++++++
 tools/mtmd/mtmd-image.h   |  6 ++++
 tools/mtmd/mtmd.cpp       |  5 ++++
 3 files changed, 73 insertions(+)

diff --git a/tools/mtmd/mtmd-image.cpp b/tools/mtmd/mtmd-image.cpp
index 72d35fce69..7c3c585ad0 100644
--- a/tools/mtmd/mtmd-image.cpp
+++ b/tools/mtmd/mtmd-image.cpp
@@ -1591,3 +1591,65 @@ mtmd_image_preproc_out mtmd_image_preprocessor_granite::preprocess(const clip_im
     }
     return output;
 }
+
+//
+// mtmd_image_preprocessor_onyx
+//
+
+// Replicates transformers' get_aspect_ratio_preserving_size (image_processing_onyx.py)
+static clip_image_size onyx_grid_size(int img_w, int img_h, int patch_hw, int max_tokens) {
+    double i_nph = (double) img_h / patch_hw;
+    double i_npw = (double) img_w / patch_hw;
+    const double ratio = i_nph > 0.0 ? i_npw / i_nph : 1.0;
+    if (i_nph * i_npw > (double) max_tokens) {
+        i_nph = std::sqrt((double) max_tokens / ratio);
+        i_npw = i_nph * ratio;
+    }
+    const int hs[2] = { (int) std::floor(i_nph), (int) std::ceil(i_nph) };
+    const int ws[2] = { (int) std::floor(i_npw), (int) std::ceil(i_npw) };
+    const double target_ar = (double) img_h / (double) img_w;
+    int    best_nph = -1;
+    int    best_npw = -1;
+    double best_d   = 0.0;
+    for (int a = 0; a < 2; ++a) {
+        for (int b = 0; b < 2; ++b) {
+            const int nph = hs[a];
+            const int npw = ws[b];
+            if (nph < 1 || npw < 1 || nph * npw > max_tokens) {
+                continue;
+            }
+            const double d = std::fabs((double) nph / (double) npw - target_ar);
+            const int n_tokens      = nph * npw;
+            const int best_n_tokens = best_nph * best_npw;
+            if (best_nph < 0 || d < best_d || (d == best_d && n_tokens > best_n_tokens)) {
+                best_nph = nph;
+                best_npw = npw;
+                best_d   = d;
+            }
+        }
+    }
+    if (best_nph < 0) { // no candidate fit under the cap: round and clamp
+        best_nph = std::max(1, (int) std::lround(i_nph));
+        best_npw = std::max(1, (int) std::lround(i_npw));
+    }
+    return clip_image_size{ best_npw * patch_hw, best_nph * patch_hw };
+}
+
+mtmd_image_preproc_out mtmd_image_preprocessor_onyx::preprocess(const clip_image_u8 & img) {
+    const int patch_hw   = hparams.patch_size * hparams.n_merge;
+    const int patch_area = hparams.patch_size * hparams.patch_size * hparams.n_merge * hparams.n_merge;
+    GGML_ASSERT(patch_area > 0 && hparams.image_max_pixels > 0);
+    const int max_tokens = hparams.image_max_pixels / patch_area;
+
+    const clip_image_size original_size = img.get_size();
+    const clip_image_size target_size   = onyx_grid_size(
+        original_size.width, original_size.height, patch_hw, max_tokens);
+
+    // PIL resizes directly to (target_w, target_h) -- a stretch, no padding.
+    clip_image_u8 resized_image;
+    img_tool::resize(img, resized_image, target_size, hparams.image_resize_algo, PAD_NONE);
+
+    mtmd_image_preproc_out output;
+    output.append(hparams, resized_image, true);
+    return output;
+}
diff --git a/tools/mtmd/mtmd-image.h b/tools/mtmd/mtmd-image.h
index 115cba51e8..26fd84d485 100644
--- a/tools/mtmd/mtmd-image.h
+++ b/tools/mtmd/mtmd-image.h
@@ -224,3 +224,9 @@ struct mtmd_image_preprocessor_granite : mtmd_image_preprocessor_llava_uhd {
     mtmd_image_preprocessor_granite(const clip_ctx * ctx) : mtmd_image_preprocessor_llava_uhd(ctx) {}
     mtmd_image_preproc_out preprocess(const clip_image_u8 & img) override;
 };
+
+// pick the patch grid closest to the input aspect ratio under the per-image token cap, stretch-resize.
+struct mtmd_image_preprocessor_onyx : mtmd_image_preprocessor {
+    mtmd_image_preprocessor_onyx(const clip_ctx * ctx) : mtmd_image_preprocessor(ctx) {}
+    mtmd_image_preproc_out preprocess(const clip_image_u8 & img) override;
+};
diff --git a/tools/mtmd/mtmd.cpp b/tools/mtmd/mtmd.cpp
index 93ca8cbcf8..5c49b35408 100644
--- a/tools/mtmd/mtmd.cpp
+++ b/tools/mtmd/mtmd.cpp
@@ -470,6 +470,11 @@ struct mtmd_context {
                     img_end = "]<]end of image[>[";
                     image_preproc = std::make_unique<mtmd_image_preprocessor_dyn_size>(ctx_v);
                 } break;
+            case PROJECTOR_TYPE_ONYX:
+                {
+                    // Follow transformers Onyx processing: <|patch|>*N, no delimiters
+                    image_preproc = std::make_unique<mtmd_image_preprocessor_onyx>(ctx_v);
+                } break;
             case PROJECTOR_TYPE_YOUTUVL:
                 {
                     // <|vision_start|> ... (image embeddings) ... <|vision_end|>