feat: add SenseNova U1.5 support

README.md

@@ -51,6 +51,7 @@ API and command-line option may change frequently.***
     - [LongCat Image](./docs/longcat_image.md)
     - [Z-Image](./docs/z_image.md)
     - [MiniT2I](./docs/minit2i.md)
+    - [SenseNova U1.5](./docs/sensenova_u1.md)
     - [Ovis-Image](./docs/ovis_image.md)
     - [Anima](./docs/anima.md)
     - [ERNIE-Image](./docs/ernie_image.md)

docs/sensenova_u1.md

@@ -0,0 +1,46 @@
+# How to Use
+
+SenseNova U1.5 is an 8B MoT model that performs diffusion directly in RGB pixel
+space. It does not require a separate text encoder or VAE.
+
+## Download weights
+
+- Download SenseNova U1.5 8B MoT
+    - safetensors: https://huggingface.co/sensenova/SenseNova-U1.5-8B-MoT
+
+Pass the complete downloaded repository directory to `--model`. The directory
+must contain `model.safetensors.index.json`, every referenced Safetensors shard,
+and the tokenizer files.
+
+## Examples
+
+### CUDA
+
+```bash
+./bin/sd-cli \
+  --model /path/to/SenseNova-U1.5-8B-MoT \
+  --prompt "a red cube on a white background" \
+  --width 2048 \
+  --height 2048 \
+  --steps 50 \
+  --cfg-scale 4 \
+  --flow-shift 3 \
+  --seed 42 \
+  --sampling-method euler \
+  --rng cuda \
+  --fa \
+  --output output.png
+```
+
+## Notes
+
+- To match the official non-thinking text-to-image pipeline, use 50 Euler
+  steps, CFG 4, flow shift 3, seed 42, CUDA RNG, and an empty negative prompt.
+- Width and height must be multiples of 32. The trained 1:1 resolution is
+  2048x2048; lower resolutions are useful for smoke tests but are outside the
+  training buckets.
+- The SenseNova prompt template and unconditional prompt are built
+  automatically.
+- This implementation supports non-thinking text-to-image generation. Image
+  editing, visual understanding, interleaved generation, and thinking-mode
+  prompt expansion are not implemented.

include/stable-diffusion.h

@@ -92,6 +92,7 @@ enum prediction_t {
     FLUX_FLOW_PRED,
     SEFI_FLOW_PRED,
     MINIT2I_FLOW_PRED,
+    SENSENOVA_U1_FLOW_PRED,
     PREDICTION_COUNT
 };
 

src/conditioning/conditioner.hpp

@@ -14,6 +14,7 @@
 #include "model/te/llm.hpp"
 #include "model/te/t5.hpp"
 #include "model_loader.h"
+#include "tokenizers/sensenova_u1_tokenizer.h"
 
 struct SDCondition {
     sd::Tensor<float> c_crossattn;
@@ -1667,6 +1668,71 @@ struct MiniT2IConditioner : public Conditioner {
     }
 };
 
+struct SenseNovaU1Conditioner : public Conditioner {
+    static constexpr size_t kMaxPromptTokens = 12288;
+    SenseNovaU1Tokenizer tokenizer;
+
+    void get_param_tensors(std::map<std::string, ggml_tensor*>& tensors) override {
+        SD_UNUSED(tensors);
+    }
+
+    void set_flash_attention_enabled(bool enabled) override {
+        SD_UNUSED(enabled);
+    }
+
+    static std::string build_query(const std::string& text, bool is_negative) {
+        static const std::string kSystemMessage =
+            "You are an image generation and editing assistant that accurately understands and executes user intent.\n\n"
+            "You support two modes:\n\n1. Think Mode:\nIf the task requires reasoning, you MUST start with a "
+            "<think></think> block. Put all reasoning inside the block using plain text. DO NOT include any image tags. "
+            "Keep it reasonable and directly useful for producing the final image.\n\n2. Non-Think Mode:\nIf no reasoning "
+            "is needed, directly produce the final image.\n\nTask Types:\n\nA. Text-to-Image Generation:\n- Generate a "
+            "high-quality image based on the user's description.\n- Ensure visual clarity, semantic consistency, and "
+            "completeness.\n- DO NOT introduce elements that contradict or override the user's intent.\n\nB. Image Editing:\n"
+            "- Use the provided image(s) as input or reference for modification or transformation.\n- The result can be an "
+            "edited image or a new image based on the reference(s).\n- Preserve all unspecified attributes unless explicitly "
+            "changed.\n\nGeneral Rules:\n- For any visible text in the image, follow the language specified for the rendered "
+            "text in the user's description, not the language of the prompt. If no language is specified, use the user's input "
+            "language.";
+
+        std::string query;
+        if (!is_negative) {
+            query += "<|im_start|>system\n";
+            query += kSystemMessage;
+            query += "<|im_end|>\n";
+        }
+        query += "<|im_start|>user\n";
+        query += text;
+        query += "<|im_end|>\n<|im_start|>assistant\n";
+        query += is_negative ? "<img>" : "<think>\n\n</think>\n\n<img>";
+        return query;
+    }
+
+    SDCondition tokenize_condition(const std::string& text, bool is_negative) {
+        auto tokens = tokenizer.encode(build_query(text, is_negative));
+        if (tokens.empty() || tokens.size() > kMaxPromptTokens) {
+            LOG_ERROR("SenseNova U1.5 prompt token count %zu is outside [1, %zu]",
+                      tokens.size(),
+                      kMaxPromptTokens);
+            return {};
+        }
+
+        SDCondition result;
+        result.c_input_ids = sd::Tensor<int32_t>({static_cast<int64_t>(tokens.size())}, tokens);
+        return result;
+    }
+
+    SDCondition get_learned_condition(int n_threads,
+                                      const ConditionerParams& conditioner_params) override {
+        SD_UNUSED(n_threads);
+        return tokenize_condition(conditioner_params.text, false);
+    }
+
+    SDCondition get_unconditional_condition(const std::string& text) {
+        return tokenize_condition(text, true);
+    }
+};
+
 struct AnimaConditioner : public Conditioner {
     std::shared_ptr<BPETokenizer> qwen_tokenizer;
     T5UniGramTokenizer t5_tokenizer;

src/model.h

@@ -57,6 +57,7 @@ enum SDVersion {
     VERSION_SEFI_IMAGE,
     VERSION_KREA2,
     VERSION_MAGE_FLOW,
+    VERSION_SENSENOVA_U1_5,
     VERSION_ESRGAN,
     VERSION_COUNT,
 };
@@ -237,6 +238,10 @@ static inline bool sd_version_is_mage_flow(SDVersion version) {
     return version == VERSION_MAGE_FLOW;
 }
 
+static inline bool sd_version_is_sensenova_u1(SDVersion version) {
+    return version == VERSION_SENSENOVA_U1_5;
+}
+
 static inline bool sd_version_uses_flux_vae(SDVersion version) {
     if (sd_version_is_flux(version) || sd_version_is_z_image(version) || sd_version_is_boogu_image(version) || sd_version_is_longcat(version)) {
         return true;
@@ -295,7 +300,8 @@ static inline bool sd_version_is_dit(SDVersion version) {
         sd_version_is_ideogram4(version) ||
         sd_version_is_sefi_image(version) ||
         sd_version_is_krea2(version) ||
-        sd_version_is_mage_flow(version)) {
+        sd_version_is_mage_flow(version) ||
+        sd_version_is_sensenova_u1(version)) {
         return true;
     }
     return false;

src/model/diffusion/model.hpp

@@ -114,6 +114,10 @@ struct MiniT2IDiffusionExtra {
     const sd::Tensor<float>* mask = nullptr;
 };
 
+struct SenseNovaU1DiffusionExtra {
+    const sd::Tensor<int32_t>* input_ids = nullptr;
+};
+
 struct HunyuanVideoDiffusionExtra {
     const sd::Tensor<float>* guidance   = nullptr;
     const sd::Tensor<float>* byt5       = nullptr;
@@ -131,6 +135,7 @@ using DiffusionExtraParams = std::variant<std::monostate,
                                           LTXAVDiffusionExtra,
                                           MiniMaxH3DiffusionExtra,
                                           MiniT2IDiffusionExtra,
+                                          SenseNovaU1DiffusionExtra,
                                           HunyuanVideoDiffusionExtra>;
 
 struct DiffusionParams {