feat: add moss-image support

README.md

@@ -46,6 +46,7 @@ API and command-line option may change frequently.***
     - [FLUX.1-dev/FLUX.1-schnell](./docs/flux.md)
     - [FLUX.2-dev/FLUX.2-klein](./docs/flux2.md)
     - [FLUX.3 Image Klein / Klein Base](./docs/flux3.md)
+    - [MOSS-Image-Base / MOSS-Image-SFT](./docs/moss_image.md)
     - [Lens](./docs/lens.md)
     - [Chroma](./docs/chroma.md)
     - [Chroma1-Radiance](./docs/chroma_radiance.md)

docs/moss_image.md

@@ -0,0 +1,34 @@
+# How to Use
+
+MOSS-Image uses a 5B diffusion transformer, the FLUX.2 VAE, and Qwen3.5 9B as the LLM text encoder. Both Base and SFT are supported. Prompt enhancement is not included.
+
+## Download weights
+
+- Download MOSS-Image Base or SFT
+    - safetensors: https://huggingface.co/Comfy-Org/MOSS-Image/tree/main/diffusion_models
+- Download vae
+    - safetensors: https://huggingface.co/Comfy-Org/MOSS-Image/tree/main/vae
+- Download Qwen3.5 9B
+    - gguf: https://huggingface.co/unsloth/Qwen3.5-9B-GGUF/tree/main
+- Download `tokenizer.json`
+    - https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base/tree/main/tokenizer
+
+Pass the external `tokenizer.json` with `--tokenizer`; Qwen3.5 uses a different vocabulary from the embedded Qwen tokenizer.
+
+## Examples
+
+### MOSS-Image Base
+
+```
+.\bin\Release\sd-cli.exe --diffusion-model ..\models\diffusion_models\moss_image_base_int8_convrot_attn.safetensors --llm ..\models\text_encoders\Qwen3.5-9B-Q4_K_M.gguf --vae ..\models\vae\flux2_ae.safetensors --tokenizer ..\models\tokenizers\tokenizer_qwen3.5.json --cfg-scale 3.0 -p "a lovely cat holding a sign says 'moss-image.cpp'" -v --offload-to-cpu -H 1024 -W 1024
+```
+
+### MOSS-Image SFT
+
+```
+.\bin\Release\sd-cli.exe --diffusion-model ..\models\diffusion_models\moss_image_sft_int8_convrot_attn.safetensors --llm ..\models\text_encoders\Qwen3.5-9B-Q4_K_M.gguf --vae ..\models\vae\flux2_ae.safetensors --tokenizer ..\models\tokenizers\tokenizer_qwen3.5.json --cfg-scale 3.0 -p "a lovely cat holding a sign says 'moss-image.cpp'" -v --offload-to-cpu -H 1024 -W 1024
+```
+
+<img src="../assets/moss/sft.png" />
+
+Use dimensions divisible by 16. The default discrete scheduler uses the upstream time shift of 5. Use `--flow-shift` to override it. The negative CFG branch skips DiT layer 22 (zero-based), matching the upstream pipeline.

src/conditioning/conditioner.hpp

@@ -1995,6 +1995,9 @@ struct LLMEmbedder : public Conditioner {
             if (sd_version_is_pid(version)) {
                 throw std::runtime_error("PiD requires an external Gemma 2 tokenizer.json; pass --tokenizer FILE or set sd_ctx_params_t::tokenizer");
             }
+            if (version == VERSION_MOSS_IMAGE) {
+                throw std::runtime_error("MOSS-Image requires the official Qwen3.5 tokenizer.json; pass --tokenizer FILE or set sd_ctx_params_t::tokenizer");
+            }
         }
         LLM::LLMArch arch = LLM::LLMArch::QWEN2_5_VL;
         if (version == VERSION_FLUX2) {
@@ -2018,6 +2021,8 @@ struct LLMEmbedder : public Conditioner {
             arch = LLM::LLMArch::QWEN3_VL;
         } else if (sd_version_is_z_image(version) || sd_version_is_z_image_l2p(version) || version == VERSION_OVIS_IMAGE || version == VERSION_FLUX2_KLEIN) {
             arch = LLM::LLMArch::QWEN3;
+        } else if (version == VERSION_MOSS_IMAGE) {
+            arch = LLM::LLMArch::QWEN3_5;
         }
         llm        = std::make_shared<LLM::LLMRunner>(arch,
                                                backend,
@@ -2032,6 +2037,8 @@ struct LLMEmbedder : public Conditioner {
             pad_id = 199999;
         } else if (arch == LLM::LLMArch::GEMMA2_2B) {
             pad_id = 0;
+        } else if (arch == LLM::LLMArch::QWEN3_5) {
+            pad_id = 248044;
         }
         tokenizer = tokenizers.create(TokenizerConfig::MAIN, llm->config.vocab_size, pad_id);
         if (!tokenizer) {
@@ -3039,6 +3046,11 @@ struct LLMEmbedder : public Conditioner {
 
                 prompt += "<|im_end|>\n<|im_start|>assistant\n";
             }
+        } else if (version == VERSION_MOSS_IMAGE) {
+            prompt_template_encode_start_idx = 0;
+            max_length                       = 4096;
+            prompt                           = "<|im_start|>user\n" + conditioner_params.text + "<|im_end|>\n<|im_start|>assistant\n<think>\n";
+            prompt_attn_range                = {0, 0};
         } else if (sd_version_is_flux3(version)) {
             prompt_template_encode_start_idx = 0;
             max_length                       = 4096;

src/model.h

@@ -67,6 +67,7 @@ enum SDVersion {
     VERSION_Z_IMAGE_L2P,
     VERSION_IRIS,
     VERSION_FLUX3,
+    VERSION_MOSS_IMAGE,
     VERSION_COUNT,
 };
 
@@ -291,7 +292,8 @@ static inline bool sd_version_uses_flux2_vae(SDVersion version) {
         sd_version_is_lens(version) ||
         sd_version_is_ideogram4(version) ||
         sd_version_is_sefi_image(version) ||
-        sd_version_is_llada_image(version)) {
+        sd_version_is_llada_image(version) ||
+        version == VERSION_MOSS_IMAGE) {
         return true;
     }
     return false;
@@ -348,7 +350,8 @@ static inline bool sd_version_is_dit(SDVersion version) {
         sd_version_is_mage_flow(version) ||
         sd_version_is_sensenova_u1(version) ||
         sd_version_is_pixart(version) ||
-        version == VERSION_IRIS) {
+        version == VERSION_IRIS ||
+        version == VERSION_MOSS_IMAGE) {
         return true;
     }
     return false;