Skip to content

Override text encoders for unet models #682

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Override text encoders for unet models #682

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions model.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1477,6 +1477,15 @@ bool ModelLoader::init_from_ckpt_file(const std::string& file_path, const std::s
return true;
}

bool ModelLoader::model_is_unet() {
for (auto& tensor_storage : tensor_storages) {
if (tensor_storage.name.find("model.diffusion_model.input_blocks.") != std::string::npos) {
return true;
}
}
return false;
}

SDVersion ModelLoader::get_sd_version() {
TensorStorage token_embedding_weight, input_block_weight;
bool input_block_checked = false;
Expand Down
1 change: 1 addition & 0 deletions model.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,6 +210,7 @@ class ModelLoader {
std::map<std::string, enum ggml_type> tensor_storages_types;

bool init_from_file(const std::string& file_path, const std::string& prefix = "");
bool model_is_unet();
SDVersion get_sd_version();
ggml_type get_sd_wtype();
ggml_type get_conditioner_wtype();
Expand Down
20 changes: 11 additions & 9 deletions stable-diffusion.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -200,16 +200,25 @@ class StableDiffusionGGML {
}
}

if (diffusion_model_path.size() > 0) {
LOG_INFO("loading diffusion model from '%s'", diffusion_model_path.c_str());
if (!model_loader.init_from_file(diffusion_model_path, "model.diffusion_model.")) {
LOG_WARN("loading diffusion model from '%s' failed", diffusion_model_path.c_str());
}
}

bool is_unet = model_loader.model_is_unet();

if (clip_l_path.size() > 0) {
LOG_INFO("loading clip_l from '%s'", clip_l_path.c_str());
if (!model_loader.init_from_file(clip_l_path, "text_encoders.clip_l.transformer.")) {
if (!model_loader.init_from_file(clip_l_path, is_unet ? "cond_stage_model.transformer." : "text_encoders.clip_l.transformer.")) {
LOG_WARN("loading clip_l from '%s' failed", clip_l_path.c_str());
}
}

if (clip_g_path.size() > 0) {
LOG_INFO("loading clip_g from '%s'", clip_g_path.c_str());
if (!model_loader.init_from_file(clip_g_path, "text_encoders.clip_g.transformer.")) {
if (!model_loader.init_from_file(clip_g_path, is_unet ? "cond_stage_model.1.transformer." : "text_encoders.clip_g.transformer.")) {
LOG_WARN("loading clip_g from '%s' failed", clip_g_path.c_str());
}
}
Expand All @@ -221,13 +230,6 @@ class StableDiffusionGGML {
}
}

if (diffusion_model_path.size() > 0) {
LOG_INFO("loading diffusion model from '%s'", diffusion_model_path.c_str());
if (!model_loader.init_from_file(diffusion_model_path, "model.diffusion_model.")) {
LOG_WARN("loading diffusion model from '%s' failed", diffusion_model_path.c_str());
}
}

if (vae_path.size() > 0) {
LOG_INFO("loading vae from '%s'", vae_path.c_str());
if (!model_loader.init_from_file(vae_path, "vae.")) {
Expand Down
Loading