Skip to content

Support 16 channel TAEs (taesd3 and taef1) #527

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

Merged
merged 1 commit into from
Dec 28, 2024
Merged

Support 16 channel TAEs (taesd3 and taef1) #527

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
2 changes: 1 addition & 1 deletion stable-diffusion.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -356,7 +356,7 @@ class StableDiffusionGGML {
first_stage_model->alloc_params_buffer();
first_stage_model->get_param_tensors(tensors, "first_stage_model");
} else {
tae_first_stage = std::make_shared<TinyAutoEncoder>(backend, model_loader.tensor_storages_types, "decoder.layers", vae_decode_only);
tae_first_stage = std::make_shared<TinyAutoEncoder>(backend, model_loader.tensor_storages_types, "decoder.layers", vae_decode_only, version);
}
// first_stage_model->get_param_tensors(tensors, "first_stage_model.");

Expand Down
23 changes: 16 additions & 7 deletions tae.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,7 +62,8 @@ class TinyEncoder : public UnaryBlock {
int num_blocks = 3;

public:
TinyEncoder() {
TinyEncoder(int z_channels = 4)
: z_channels(z_channels) {
int index = 0;
blocks[std::to_string(index++)] = std::shared_ptr<GGMLBlock>(new Conv2d(in_channels, channels, {3, 3}, {1, 1}, {1, 1}));
blocks[std::to_string(index++)] = std::shared_ptr<GGMLBlock>(new TAEBlock(channels, channels));
Expand Down Expand Up @@ -106,7 +107,10 @@ class TinyDecoder : public UnaryBlock {
int num_blocks = 3;

public:
TinyDecoder(int index = 0) {
TinyDecoder(int z_channels = 4)
: z_channels(z_channels) {
int index = 0;

blocks[std::to_string(index++)] = std::shared_ptr<GGMLBlock>(new Conv2d(z_channels, channels, {3, 3}, {1, 1}, {1, 1}));
index++; // nn.ReLU()

Expand Down Expand Up @@ -163,12 +167,16 @@ class TAESD : public GGMLBlock {
bool decode_only;

public:
TAESD(bool decode_only = true)
TAESD(bool decode_only = true, SDVersion version = VERSION_SD1)
: decode_only(decode_only) {
blocks["decoder.layers"] = std::shared_ptr<GGMLBlock>(new TinyDecoder());
int z_channels = 4;
if (sd_version_is_dit(version)) {
z_channels = 16;
}
blocks["decoder.layers"] = std::shared_ptr<GGMLBlock>(new TinyDecoder(z_channels));

if (!decode_only) {
blocks["encoder.layers"] = std::shared_ptr<GGMLBlock>(new TinyEncoder());
blocks["encoder.layers"] = std::shared_ptr<GGMLBlock>(new TinyEncoder(z_channels));
}
}

Expand All @@ -190,9 +198,10 @@ struct TinyAutoEncoder : public GGMLRunner {
TinyAutoEncoder(ggml_backend_t backend,
std::map<std::string, enum ggml_type>& tensor_types,
const std::string prefix,
bool decoder_only = true)
bool decoder_only = true,
SDVersion version = VERSION_SD1)
: decode_only(decoder_only),
taesd(decode_only),
taesd(decode_only, version),
GGMLRunner(backend) {
taesd.init(params_ctx, tensor_types, prefix);
}
Expand Down
Loading