diff options
Diffstat (limited to 'modules/textual_inversion/textual_inversion.py')
| -rw-r--r-- | modules/textual_inversion/textual_inversion.py | 23 |
1 files changed, 17 insertions, 6 deletions
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index 6166c76f..aa79dc09 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -13,7 +13,7 @@ import numpy as np from PIL import Image, PngImagePlugin
from torch.utils.tensorboard import SummaryWriter
-from modules import shared, devices, sd_hijack, processing, sd_models, images, sd_samplers, sd_hijack_checkpoint, errors, hashes
+from modules import shared, devices, sd_hijack, sd_models, images, sd_samplers, sd_hijack_checkpoint, errors, hashes
import modules.textual_inversion.dataset
from modules.textual_inversion.learn_schedule import LearnRateScheduler
@@ -181,29 +181,38 @@ class EmbeddingDatabase: else:
return
+
# textual inversion embeddings
if 'string_to_param' in data:
param_dict = data['string_to_param']
param_dict = getattr(param_dict, '_parameters', param_dict) # fix for torch 1.12.1 loading saved file from torch 1.11
assert len(param_dict) == 1, 'embedding file has multiple terms in it'
emb = next(iter(param_dict.items()))[1]
- # diffuser concepts
- elif type(data) == dict and type(next(iter(data.values()))) == torch.Tensor:
+ vec = emb.detach().to(devices.device, dtype=torch.float32)
+ shape = vec.shape[-1]
+ vectors = vec.shape[0]
+ elif type(data) == dict and 'clip_g' in data and 'clip_l' in data: # SDXL embedding
+ vec = {k: v.detach().to(devices.device, dtype=torch.float32) for k, v in data.items()}
+ shape = data['clip_g'].shape[-1] + data['clip_l'].shape[-1]
+ vectors = data['clip_g'].shape[0]
+ elif type(data) == dict and type(next(iter(data.values()))) == torch.Tensor: # diffuser concepts
assert len(data.keys()) == 1, 'embedding file has multiple terms in it'
emb = next(iter(data.values()))
if len(emb.shape) == 1:
emb = emb.unsqueeze(0)
+ vec = emb.detach().to(devices.device, dtype=torch.float32)
+ shape = vec.shape[-1]
+ vectors = vec.shape[0]
else:
raise Exception(f"Couldn't identify {filename} as neither textual inversion embedding nor diffuser concept.")
- vec = emb.detach().to(devices.device, dtype=torch.float32)
embedding = Embedding(vec, name)
embedding.step = data.get('step', None)
embedding.sd_checkpoint = data.get('sd_checkpoint', None)
embedding.sd_checkpoint_name = data.get('sd_checkpoint_name', None)
- embedding.vectors = vec.shape[0]
- embedding.shape = vec.shape[-1]
+ embedding.vectors = vectors
+ embedding.shape = shape
embedding.filename = path
embedding.set_hash(hashes.sha256(embedding.filename, "textual_inversion/" + name) or '')
@@ -378,6 +387,8 @@ def validate_train_inputs(model_name, learn_rate, batch_size, gradient_step, dat def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, use_weight, create_image_every, save_embedding_every, template_filename, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
+ from modules import processing
+
save_embedding_every = save_embedding_every or 0
create_image_every = create_image_every or 0
template_file = textual_inversion_templates.get(template_filename, None)
|