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 moss-image support (#2148)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-10-17 03:38:38 +08:00
1 parent af0fc72c96
commit 68285df319
11 files changed
+508 -10
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/conditioning/conditioner.hpp
+12
View File
@@ -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;