From cc92dc1f8d73dd4d574c4c8ccab78b7fc61e440b Mon Sep 17 00:00:00 2001 From: ssysm Date: Sun, 9 Oct 2022 23:17:29 -0400 Subject: add vae path args --- modules/shared.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'modules/shared.py') diff --git a/modules/shared.py b/modules/shared.py index 2dc092d6..52ccfa6e 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -64,7 +64,7 @@ parser.add_argument("--autolaunch", action='store_true', help="open the webui UR parser.add_argument("--use-textbox-seed", action='store_true', help="use textbox for seeds in UI (no up/down, but possible to input long seeds)", default=False) parser.add_argument("--disable-console-progressbars", action='store_true', help="do not output progressbars to console", default=False) parser.add_argument("--enable-console-prompts", action='store_true', help="print prompts to console when generating with txt2img and img2img", default=False) - +parser.add_argument('--vae-path', type=str, help='Path to Variational Autoencoders model', default=None) cmd_opts = parser.parse_args() -- cgit v1.2.3 From 39919c40dd18f5a14ae21403efea1b0f819756c7 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Mon, 10 Oct 2022 20:32:37 +0300 Subject: add eta noise seed delta option --- javascript/hints.js | 1 + modules/processing.py | 6 +++++- modules/shared.py | 1 + 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'modules/shared.py') diff --git a/javascript/hints.js b/javascript/hints.js index 8e352e94..47b80776 100644 --- a/javascript/hints.js +++ b/javascript/hints.js @@ -79,6 +79,7 @@ titles = { "Highres. fix": "Use a two step process to partially create an image at smaller resolution, upscale, and then improve details in it without changing composition", "Scale latent": "Uscale the image in latent space. Alternative is to produce the full image from latent representation, upscale that, and then move it back to latent space.", + "Eta noise seed delta": "If this values is non-zero, it will be added to seed and used to initialize RNG for noises when using samplers with Eta. You can use this to produce even more variation of images, or you can use this to match images of other software if you know what you are doing.", } diff --git a/modules/processing.py b/modules/processing.py index 50ba4fc5..698b3069 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -207,7 +207,7 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see # enables the generation of additional tensors with noise that the sampler will use during its processing. # Using those pre-generated tensors instead of simple torch.randn allows a batch with seeds [100, 101] to # produce the same images as with two batches [100], [101]. - if p is not None and p.sampler is not None and len(seeds) > 1 and opts.enable_batch_seeds: + if p is not None and p.sampler is not None and (len(seeds) > 1 and opts.enable_batch_seeds or opts.eta_noise_seed_delta > 0): sampler_noises = [[] for _ in range(p.sampler.number_of_needed_noises(p))] else: sampler_noises = None @@ -247,6 +247,9 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see if sampler_noises is not None: cnt = p.sampler.number_of_needed_noises(p) + if opts.eta_noise_seed_delta > 0: + torch.manual_seed(seed + opts.eta_noise_seed_delta) + for j in range(cnt): sampler_noises[j].append(devices.randn_without_seed(tuple(noise_shape))) @@ -301,6 +304,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration "Denoising strength": getattr(p, 'denoising_strength', None), "Eta": (None if p.sampler is None or p.sampler.eta == p.sampler.default_eta else p.sampler.eta), "Clip skip": None if clip_skip <= 1 else clip_skip, + "ENSD": None if opts.eta_noise_seed_delta == 0 else opts.eta_noise_seed_delta, } generation_params.update(p.extra_generation_params) diff --git a/modules/shared.py b/modules/shared.py index 5dfc344c..b1c65ecf 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -260,6 +260,7 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters" 's_churn': OptionInfo(0.0, "sigma churn", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), 's_tmin': OptionInfo(0.0, "sigma tmin", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), 's_noise': OptionInfo(1.0, "sigma noise", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), + 'eta_noise_seed_delta': OptionInfo(0, "Eta noise seed delta", gr.Number, {"precision": 0}), })) -- cgit v1.2.3 From f98338faa84ecce503e68d8ba13d5f7bbae52730 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Mon, 10 Oct 2022 23:15:48 +0300 Subject: add an option to not add watermark to created images --- javascript/hints.js | 1 + modules/shared.py | 1 + 2 files changed, 2 insertions(+) (limited to 'modules/shared.py') diff --git a/javascript/hints.js b/javascript/hints.js index 47b80776..045f2d3c 100644 --- a/javascript/hints.js +++ b/javascript/hints.js @@ -80,6 +80,7 @@ titles = { "Scale latent": "Uscale the image in latent space. Alternative is to produce the full image from latent representation, upscale that, and then move it back to latent space.", "Eta noise seed delta": "If this values is non-zero, it will be added to seed and used to initialize RNG for noises when using samplers with Eta. You can use this to produce even more variation of images, or you can use this to match images of other software if you know what you are doing.", + "Do not add watermark to images": "If this option is enabled, watermark will not be added to created images. Warning: if you do not add watermark, you may be bevaing in an unethical manner.", } diff --git a/modules/shared.py b/modules/shared.py index da389f9c..ecd15ef5 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -173,6 +173,7 @@ options_templates.update(options_section(('saving-images', "Saving images/grids" "use_original_name_batch": OptionInfo(False, "Use original name for output filename during batch process in extras tab"), "save_selected_only": OptionInfo(True, "When using 'Save' button, only save a single selected image"), + "do_not_add_watermark": OptionInfo(False, "Do not add watermark to images"), })) options_templates.update(options_section(('saving-paths', "Paths for saving"), { -- cgit v1.2.3 From 8617396c6df71074c7fd3d39419802026874712a Mon Sep 17 00:00:00 2001 From: Kenneth Date: Mon, 10 Oct 2022 17:23:07 -0600 Subject: Added slider for deepbooru score threshold in settings --- modules/shared.py | 1 + modules/ui.py | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'modules/shared.py') diff --git a/modules/shared.py b/modules/shared.py index ecd15ef5..e0830e28 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -239,6 +239,7 @@ options_templates.update(options_section(('interrogate', "Interrogate Options"), "interrogate_clip_min_length": OptionInfo(24, "Interrogate: minimum description length (excluding artists, etc..)", gr.Slider, {"minimum": 1, "maximum": 128, "step": 1}), "interrogate_clip_max_length": OptionInfo(48, "Interrogate: maximum description length", gr.Slider, {"minimum": 1, "maximum": 256, "step": 1}), "interrogate_clip_dict_limit": OptionInfo(1500, "Interrogate: maximum number of lines in text file (0 = No limit)"), + "interrogate_deepbooru_score_threshold": OptionInfo(0.5, "Interrogate: deepbooru score threshold", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01}), })) options_templates.update(options_section(('ui', "User interface"), { diff --git a/modules/ui.py b/modules/ui.py index cafda884..ca3151c4 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -311,7 +311,7 @@ def interrogate(image): def interrogate_deepbooru(image): - prompt = get_deepbooru_tags(image) + prompt = get_deepbooru_tags(image, opts.interrogate_deepbooru_score_threshold) return gr_show(True) if prompt is None else prompt -- cgit v1.2.3 From 5e2627a1a63e4c9f87e6e604ecc24e9936f149de Mon Sep 17 00:00:00 2001 From: hentailord85ez <112723046+hentailord85ez@users.noreply.github.com> Date: Tue, 11 Oct 2022 07:55:28 +0100 Subject: Comma backtrack padding (#2192) Comma backtrack padding --- modules/sd_hijack.py | 19 ++++++++++++++++++- modules/shared.py | 1 + 2 files changed, 19 insertions(+), 1 deletion(-) (limited to 'modules/shared.py') diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index 827bf304..aa4d2cbc 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -107,6 +107,8 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): self.tokenizer = wrapped.tokenizer self.token_mults = {} + self.comma_token = [v for k, v in self.tokenizer.get_vocab().items() if k == ','][0] + tokens_with_parens = [(k, v) for k, v in self.tokenizer.get_vocab().items() if '(' in k or ')' in k or '[' in k or ']' in k] for text, ident in tokens_with_parens: mult = 1.0 @@ -136,6 +138,7 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): fixes = [] remade_tokens = [] multipliers = [] + last_comma = -1 for tokens, (text, weight) in zip(tokenized, parsed): i = 0 @@ -144,6 +147,20 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): embedding, embedding_length_in_tokens = self.hijack.embedding_db.find_embedding_at_position(tokens, i) + if token == self.comma_token: + last_comma = len(remade_tokens) + elif opts.comma_padding_backtrack != 0 and max(len(remade_tokens), 1) % 75 == 0 and last_comma != -1 and len(remade_tokens) - last_comma <= opts.comma_padding_backtrack: + last_comma += 1 + reloc_tokens = remade_tokens[last_comma:] + reloc_mults = multipliers[last_comma:] + + remade_tokens = remade_tokens[:last_comma] + length = len(remade_tokens) + + rem = int(math.ceil(length / 75)) * 75 - length + remade_tokens += [id_end] * rem + reloc_tokens + multipliers = multipliers[:last_comma] + [1.0] * rem + reloc_mults + if embedding is None: remade_tokens.append(token) multipliers.append(weight) @@ -284,7 +301,7 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): while max(map(len, remade_batch_tokens)) != 0: rem_tokens = [x[75:] for x in remade_batch_tokens] rem_multipliers = [x[75:] for x in batch_multipliers] - + self.hijack.fixes = [] for unfiltered in hijack_fixes: fixes = [] diff --git a/modules/shared.py b/modules/shared.py index e0830e28..14b40d70 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -227,6 +227,7 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), { "enable_emphasis": OptionInfo(True, "Emphasis: use (text) to make model pay more attention to text and [text] to make it pay less attention"), "use_old_emphasis_implementation": OptionInfo(False, "Use old emphasis implementation. Can be useful to reproduce old seeds."), "enable_batch_seeds": OptionInfo(True, "Make K-diffusion samplers produce same images in a batch as when making a single image"), + "comma_padding_backtrack": OptionInfo(20, "Increase coherency by padding from the last comma within n tokens when using more than 75 tokens", gr.Slider, {"minimum": 0, "maximum": 74, "step": 1 }), "filter_nsfw": OptionInfo(False, "Filter NSFW content"), 'CLIP_stop_at_last_layers': OptionInfo(1, "Stop At last layers of CLIP model", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}), "random_artist_categories": OptionInfo([], "Allowed categories for random artists selection when using the Roll button", gr.CheckboxGroup, {"choices": artist_db.categories()}), -- cgit v1.2.3 From 530103b586109c11fd068eb70ef09503ec6a4caf Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Tue, 11 Oct 2022 14:53:02 +0300 Subject: fixes related to merge --- modules/hypernetwork.py | 103 ------------------------- modules/hypernetwork/hypernetwork.py | 74 +++++++++++------- modules/hypernetwork/ui.py | 10 +-- modules/sd_hijack_optimizations.py | 3 +- modules/shared.py | 13 +++- modules/textual_inversion/textual_inversion.py | 12 +-- modules/ui.py | 5 +- scripts/xy_grid.py | 3 +- webui.py | 15 +--- 9 files changed, 78 insertions(+), 160 deletions(-) delete mode 100644 modules/hypernetwork.py (limited to 'modules/shared.py') diff --git a/modules/hypernetwork.py b/modules/hypernetwork.py deleted file mode 100644 index 7bbc443e..00000000 --- a/modules/hypernetwork.py +++ /dev/null @@ -1,103 +0,0 @@ -import glob -import os -import sys -import traceback - -import torch - -from ldm.util import default -from modules import devices, shared -import torch -from torch import einsum -from einops import rearrange, repeat - - -class HypernetworkModule(torch.nn.Module): - def __init__(self, dim, state_dict): - super().__init__() - - self.linear1 = torch.nn.Linear(dim, dim * 2) - self.linear2 = torch.nn.Linear(dim * 2, dim) - - self.load_state_dict(state_dict, strict=True) - self.to(devices.device) - - def forward(self, x): - return x + (self.linear2(self.linear1(x))) - - -class Hypernetwork: - filename = None - name = None - - def __init__(self, filename): - self.filename = filename - self.name = os.path.splitext(os.path.basename(filename))[0] - self.layers = {} - - state_dict = torch.load(filename, map_location='cpu') - for size, sd in state_dict.items(): - self.layers[size] = (HypernetworkModule(size, sd[0]), HypernetworkModule(size, sd[1])) - - -def list_hypernetworks(path): - res = {} - for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True): - name = os.path.splitext(os.path.basename(filename))[0] - res[name] = filename - return res - - -def load_hypernetwork(filename): - path = shared.hypernetworks.get(filename, None) - if path is not None: - print(f"Loading hypernetwork {filename}") - try: - shared.loaded_hypernetwork = Hypernetwork(path) - except Exception: - print(f"Error loading hypernetwork {path}", file=sys.stderr) - print(traceback.format_exc(), file=sys.stderr) - else: - if shared.loaded_hypernetwork is not None: - print(f"Unloading hypernetwork") - - shared.loaded_hypernetwork = None - - -def apply_hypernetwork(hypernetwork, context): - hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None) - - if hypernetwork_layers is None: - return context, context - - context_k = hypernetwork_layers[0](context) - context_v = hypernetwork_layers[1](context) - return context_k, context_v - - -def attention_CrossAttention_forward(self, x, context=None, mask=None): - h = self.heads - - q = self.to_q(x) - context = default(context, x) - - context_k, context_v = apply_hypernetwork(shared.loaded_hypernetwork, context) - k = self.to_k(context_k) - v = self.to_v(context_v) - - q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v)) - - sim = einsum('b i d, b j d -> b i j', q, k) * self.scale - - if mask is not None: - mask = rearrange(mask, 'b ... -> b (...)') - max_neg_value = -torch.finfo(sim.dtype).max - mask = repeat(mask, 'b j -> (b h) () j', h=h) - sim.masked_fill_(~mask, max_neg_value) - - # attention, what we cannot get enough of - attn = sim.softmax(dim=-1) - - out = einsum('b i j, b j d -> b i d', attn, v) - out = rearrange(out, '(b h) n d -> b n (h d)', h=h) - return self.to_out(out) diff --git a/modules/hypernetwork/hypernetwork.py b/modules/hypernetwork/hypernetwork.py index a3d6a47e..aa701bda 100644 --- a/modules/hypernetwork/hypernetwork.py +++ b/modules/hypernetwork/hypernetwork.py @@ -26,10 +26,11 @@ class HypernetworkModule(torch.nn.Module): if state_dict is not None: self.load_state_dict(state_dict, strict=True) else: - self.linear1.weight.data.fill_(0.0001) - self.linear1.bias.data.fill_(0.0001) - self.linear2.weight.data.fill_(0.0001) - self.linear2.bias.data.fill_(0.0001) + + self.linear1.weight.data.normal_(mean=0.0, std=0.01) + self.linear1.bias.data.zero_() + self.linear2.weight.data.normal_(mean=0.0, std=0.01) + self.linear2.bias.data.zero_() self.to(devices.device) @@ -92,41 +93,54 @@ class Hypernetwork: self.sd_checkpoint_name = state_dict.get('sd_checkpoint_name', None) -def load_hypernetworks(path): +def list_hypernetworks(path): res = {} + for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True): + name = os.path.splitext(os.path.basename(filename))[0] + res[name] = filename + return res - for filename in glob.iglob(path + '**/*.pt', recursive=True): + +def load_hypernetwork(filename): + path = shared.hypernetworks.get(filename, None) + if path is not None: + print(f"Loading hypernetwork {filename}") try: - hn = Hypernetwork() - hn.load(filename) - res[hn.name] = hn + shared.loaded_hypernetwork = Hypernetwork() + shared.loaded_hypernetwork.load(path) + except Exception: - print(f"Error loading hypernetwork {filename}", file=sys.stderr) + print(f"Error loading hypernetwork {path}", file=sys.stderr) print(traceback.format_exc(), file=sys.stderr) + else: + if shared.loaded_hypernetwork is not None: + print(f"Unloading hypernetwork") - return res + shared.loaded_hypernetwork = None -def attention_CrossAttention_forward(self, x, context=None, mask=None): - h = self.heads +def apply_hypernetwork(hypernetwork, context, layer=None): + hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None) - q = self.to_q(x) - context = default(context, x) + if hypernetwork_layers is None: + return context, context - hypernetwork_layers = (shared.hypernetwork.layers if shared.hypernetwork is not None else {}).get(context.shape[2], None) + if layer is not None: + layer.hyper_k = hypernetwork_layers[0] + layer.hyper_v = hypernetwork_layers[1] - if hypernetwork_layers is not None: - hypernetwork_k, hypernetwork_v = hypernetwork_layers + context_k = hypernetwork_layers[0](context) + context_v = hypernetwork_layers[1](context) + return context_k, context_v - self.hypernetwork_k = hypernetwork_k - self.hypernetwork_v = hypernetwork_v - context_k = hypernetwork_k(context) - context_v = hypernetwork_v(context) - else: - context_k = context - context_v = context +def attention_CrossAttention_forward(self, x, context=None, mask=None): + h = self.heads + + q = self.to_q(x) + context = default(context, x) + context_k, context_v = apply_hypernetwork(shared.loaded_hypernetwork, context, self) k = self.to_k(context_k) v = self.to_v(context_v) @@ -151,7 +165,9 @@ def attention_CrossAttention_forward(self, x, context=None, mask=None): def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory, steps, create_image_every, save_hypernetwork_every, template_file, preview_image_prompt): assert hypernetwork_name, 'embedding not selected' - shared.hypernetwork = shared.hypernetworks[hypernetwork_name] + path = shared.hypernetworks.get(hypernetwork_name, None) + shared.loaded_hypernetwork = Hypernetwork() + shared.loaded_hypernetwork.load(path) shared.state.textinfo = "Initializing hypernetwork training..." shared.state.job_count = steps @@ -176,9 +192,9 @@ def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory, shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..." with torch.autocast("cuda"): - ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, size=512, placeholder_token=hypernetwork_name, model=shared.sd_model, device=devices.device, template_file=template_file) + ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=512, height=512, repeats=1, placeholder_token=hypernetwork_name, model=shared.sd_model, device=devices.device, template_file=template_file) - hypernetwork = shared.hypernetworks[hypernetwork_name] + hypernetwork = shared.loaded_hypernetwork weights = hypernetwork.weights() for weight in weights: weight.requires_grad = True @@ -194,7 +210,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory, if ititial_step > steps: return hypernetwork, filename - pbar = tqdm.tqdm(enumerate(ds), total=steps-ititial_step) + pbar = tqdm.tqdm(enumerate(ds), total=steps - ititial_step) for i, (x, text) in pbar: hypernetwork.step = i + ititial_step diff --git a/modules/hypernetwork/ui.py b/modules/hypernetwork/ui.py index 525f978c..f6d1d0a3 100644 --- a/modules/hypernetwork/ui.py +++ b/modules/hypernetwork/ui.py @@ -6,24 +6,24 @@ import gradio as gr import modules.textual_inversion.textual_inversion import modules.textual_inversion.preprocess from modules import sd_hijack, shared +from modules.hypernetwork import hypernetwork def create_hypernetwork(name): fn = os.path.join(shared.cmd_opts.hypernetwork_dir, f"{name}.pt") assert not os.path.exists(fn), f"file {fn} already exists" - hypernetwork = modules.hypernetwork.hypernetwork.Hypernetwork(name=name) - hypernetwork.save(fn) + hypernet = modules.hypernetwork.hypernetwork.Hypernetwork(name=name) + hypernet.save(fn) shared.reload_hypernetworks() - shared.hypernetwork = shared.hypernetworks.get(shared.opts.sd_hypernetwork, None) return gr.Dropdown.update(choices=sorted([x for x in shared.hypernetworks.keys()])), f"Created: {fn}", "" def train_hypernetwork(*args): - initial_hypernetwork = shared.hypernetwork + initial_hypernetwork = shared.loaded_hypernetwork try: sd_hijack.undo_optimizations() @@ -38,6 +38,6 @@ Hypernetwork saved to {html.escape(filename)} except Exception: raise finally: - shared.hypernetwork = initial_hypernetwork + shared.loaded_hypernetwork = initial_hypernetwork sd_hijack.apply_optimizations() diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py index 25cb67a4..27e571fc 100644 --- a/modules/sd_hijack_optimizations.py +++ b/modules/sd_hijack_optimizations.py @@ -8,7 +8,8 @@ from torch import einsum from ldm.util import default from einops import rearrange -from modules import shared, hypernetwork +from modules import shared +from modules.hypernetwork import hypernetwork if shared.cmd_opts.xformers or shared.cmd_opts.force_enable_xformers: diff --git a/modules/shared.py b/modules/shared.py index 14b40d70..8753015e 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -13,7 +13,8 @@ import modules.memmon import modules.sd_models import modules.styles import modules.devices as devices -from modules import sd_samplers, hypernetwork +from modules import sd_samplers +from modules.hypernetwork import hypernetwork from modules.paths import models_path, script_path, sd_path sd_model_file = os.path.join(script_path, 'model.ckpt') @@ -29,6 +30,7 @@ parser.add_argument("--no-half-vae", action='store_true', help="do not switch th parser.add_argument("--no-progressbar-hiding", action='store_true', help="do not hide progressbar in gradio UI (we hide it because it slows down ML if you have hardware acceleration in browser)") parser.add_argument("--max-batch-count", type=int, default=16, help="maximum batch count value for the UI") parser.add_argument("--embeddings-dir", type=str, default=os.path.join(script_path, 'embeddings'), help="embeddings directory for textual inversion (default: embeddings)") +parser.add_argument("--hypernetwork-dir", type=str, default=os.path.join(models_path, 'hypernetworks'), help="hypernetwork directory") parser.add_argument("--allow-code", action='store_true', help="allow custom script execution from webui") parser.add_argument("--medvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a little speed for low VRM usage") parser.add_argument("--lowvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a lot of speed for very low VRM usage") @@ -82,10 +84,17 @@ parallel_processing_allowed = not cmd_opts.lowvram and not cmd_opts.medvram xformers_available = False config_filename = cmd_opts.ui_settings_file -hypernetworks = hypernetwork.list_hypernetworks(os.path.join(models_path, 'hypernetworks')) +hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir) loaded_hypernetwork = None +def reload_hypernetworks(): + global hypernetworks + + hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir) + hypernetwork.load_hypernetwork(opts.sd_hypernetwork) + + class State: skipped = False interrupted = False diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index 5965c5a0..d6977950 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -156,7 +156,7 @@ def create_embedding(name, num_vectors_per_token, init_text='*'): return fn -def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_width, training_height, steps, num_repeats, create_image_every, save_embedding_every, template_file): +def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_width, training_height, steps, num_repeats, create_image_every, save_embedding_every, template_file, preview_image_prompt): assert embedding_name, 'embedding not selected' shared.state.textinfo = "Initializing textual inversion training..." @@ -238,12 +238,14 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini if embedding.step > 0 and images_dir is not None and embedding.step % create_image_every == 0: last_saved_image = os.path.join(images_dir, f'{embedding_name}-{embedding.step}.png') + preview_text = text if preview_image_prompt == "" else preview_image_prompt + p = processing.StableDiffusionProcessingTxt2Img( sd_model=shared.sd_model, - prompt=text, + prompt=preview_text, steps=20, - height=training_height, - width=training_width, + height=training_height, + width=training_width, do_not_save_grid=True, do_not_save_samples=True, ) @@ -254,7 +256,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini shared.state.current_image = image image.save(last_saved_image) - last_saved_image += f", prompt: {text}" + last_saved_image += f", prompt: {preview_text}" shared.state.job_no = embedding.step diff --git a/modules/ui.py b/modules/ui.py index 10b1ee3a..df653059 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1023,7 +1023,7 @@ def create_ui(wrap_gradio_gpu_call): gr.HTML(value="") with gr.Column(): - create_embedding = gr.Button(value="Create", variant='primary') + create_embedding = gr.Button(value="Create embedding", variant='primary') with gr.Group(): gr.HTML(value="

Create a new hypernetwork

") @@ -1035,7 +1035,7 @@ def create_ui(wrap_gradio_gpu_call): gr.HTML(value="") with gr.Column(): - create_hypernetwork = gr.Button(value="Create", variant='primary') + create_hypernetwork = gr.Button(value="Create hypernetwork", variant='primary') with gr.Group(): gr.HTML(value="

Preprocess images

") @@ -1147,6 +1147,7 @@ def create_ui(wrap_gradio_gpu_call): create_image_every, save_embedding_every, template_file, + preview_image_prompt, ], outputs=[ ti_output, diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py index 42e1489c..0af5993c 100644 --- a/scripts/xy_grid.py +++ b/scripts/xy_grid.py @@ -10,7 +10,8 @@ import numpy as np import modules.scripts as scripts import gradio as gr -from modules import images, hypernetwork +from modules import images +from modules.hypernetwork import hypernetwork from modules.processing import process_images, Processed, get_correct_sampler from modules.shared import opts, cmd_opts, state import modules.shared as shared diff --git a/webui.py b/webui.py index 7c200551..ba2156c8 100644 --- a/webui.py +++ b/webui.py @@ -29,6 +29,7 @@ from modules import devices from modules import modelloader from modules.paths import script_path from modules.shared import cmd_opts +import modules.hypernetwork.hypernetwork modelloader.cleanup_models() modules.sd_models.setup_model() @@ -77,22 +78,12 @@ def wrap_gradio_gpu_call(func, extra_outputs=None): return modules.ui.wrap_gradio_call(f, extra_outputs=extra_outputs) -def set_hypernetwork(): - shared.hypernetwork = shared.hypernetworks.get(shared.opts.sd_hypernetwork, None) - - -shared.reload_hypernetworks() -shared.opts.onchange("sd_hypernetwork", set_hypernetwork) -set_hypernetwork() - - modules.scripts.load_scripts(os.path.join(script_path, "scripts")) shared.sd_model = modules.sd_models.load_model() shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: modules.sd_models.reload_model_weights(shared.sd_model))) -loaded_hypernetwork = modules.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork) -shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: modules.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork))) +shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: modules.hypernetwork.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork))) def webui(): @@ -117,7 +108,7 @@ def webui(): prevent_thread_lock=True ) - app.add_middleware(GZipMiddleware,minimum_size=1000) + app.add_middleware(GZipMiddleware, minimum_size=1000) while 1: time.sleep(0.5) -- cgit v1.2.3 From 59925644480b6fd84f6bb84b4df7d4fbc6a0cce8 Mon Sep 17 00:00:00 2001 From: JamnedZ Date: Tue, 11 Oct 2022 16:40:27 +0700 Subject: Cleaned ngrok integration --- modules/ngrok.py | 15 +++++++++++++++ modules/shared.py | 1 + modules/ui.py | 5 +++++ 3 files changed, 21 insertions(+) create mode 100644 modules/ngrok.py (limited to 'modules/shared.py') diff --git a/modules/ngrok.py b/modules/ngrok.py new file mode 100644 index 00000000..17e6976f --- /dev/null +++ b/modules/ngrok.py @@ -0,0 +1,15 @@ +from pyngrok import ngrok, conf, exception + + +def connect(token, port): + if token == None: + token = 'None' + conf.get_default().auth_token = token + try: + public_url = ngrok.connect(port).public_url + except exception.PyngrokNgrokError: + print(f'Invalid ngrok authtoken, ngrok connection aborted.\n' + f'Your token: {token}, get the right one on https://dashboard.ngrok.com/get-started/your-authtoken') + else: + print(f'ngrok connected to localhost:{port}! URL: {public_url}\n' + 'You can use this link after the launch is complete.') \ No newline at end of file diff --git a/modules/shared.py b/modules/shared.py index 8753015e..375e3afb 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -38,6 +38,7 @@ parser.add_argument("--always-batch-cond-uncond", action='store_true', help="dis parser.add_argument("--unload-gfpgan", action='store_true', help="does not do anything.") parser.add_argument("--precision", type=str, help="evaluate at this precision", choices=["full", "autocast"], default="autocast") parser.add_argument("--share", action='store_true', help="use share=True for gradio and make the UI accessible through their site (doesn't work for me but you might have better luck)") +parser.add_argument("--ngrok", type=str, help="ngrok authtoken, alternative to gradio --share", default=None) parser.add_argument("--codeformer-models-path", type=str, help="Path to directory with codeformer model file(s).", default=os.path.join(models_path, 'Codeformer')) parser.add_argument("--gfpgan-models-path", type=str, help="Path to directory with GFPGAN model file(s).", default=os.path.join(models_path, 'GFPGAN')) parser.add_argument("--esrgan-models-path", type=str, help="Path to directory with ESRGAN model file(s).", default=os.path.join(models_path, 'ESRGAN')) diff --git a/modules/ui.py b/modules/ui.py index fc0f3d3c..f57f32db 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -51,6 +51,11 @@ if not cmd_opts.share and not cmd_opts.listen: gradio.utils.version_check = lambda: None gradio.utils.get_local_ip_address = lambda: '127.0.0.1' +if cmd_opts.ngrok != None: + import modules.ngrok as ngrok + print('ngrok authtoken detected, trying to connect...') + ngrok.connect(cmd_opts.ngrok, cmd_opts.port if cmd_opts.port != None else 7860) + def gr_show(visible=True): return {"visible": visible, "__type__": "update"} -- cgit v1.2.3 From 873efeed49bb5197a42da18272115b326c5d68f3 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Tue, 11 Oct 2022 15:51:22 +0300 Subject: rename hypernetwork dir to hypernetworks to prevent clash with an old filename that people who use zip instead of git clone will have --- modules/hypernetwork/hypernetwork.py | 283 ---------------------------------- modules/hypernetwork/ui.py | 43 ------ modules/hypernetworks/hypernetwork.py | 283 ++++++++++++++++++++++++++++++++++ modules/hypernetworks/ui.py | 43 ++++++ modules/sd_hijack.py | 2 +- modules/sd_hijack_optimizations.py | 2 +- modules/shared.py | 2 +- modules/ui.py | 2 +- scripts/xy_grid.py | 2 +- webui.py | 2 +- 10 files changed, 332 insertions(+), 332 deletions(-) delete mode 100644 modules/hypernetwork/hypernetwork.py delete mode 100644 modules/hypernetwork/ui.py create mode 100644 modules/hypernetworks/hypernetwork.py create mode 100644 modules/hypernetworks/ui.py (limited to 'modules/shared.py') diff --git a/modules/hypernetwork/hypernetwork.py b/modules/hypernetwork/hypernetwork.py deleted file mode 100644 index aa701bda..00000000 --- a/modules/hypernetwork/hypernetwork.py +++ /dev/null @@ -1,283 +0,0 @@ -import datetime -import glob -import html -import os -import sys -import traceback -import tqdm - -import torch - -from ldm.util import default -from modules import devices, shared, processing, sd_models -import torch -from torch import einsum -from einops import rearrange, repeat -import modules.textual_inversion.dataset - - -class HypernetworkModule(torch.nn.Module): - def __init__(self, dim, state_dict=None): - super().__init__() - - self.linear1 = torch.nn.Linear(dim, dim * 2) - self.linear2 = torch.nn.Linear(dim * 2, dim) - - if state_dict is not None: - self.load_state_dict(state_dict, strict=True) - else: - - self.linear1.weight.data.normal_(mean=0.0, std=0.01) - self.linear1.bias.data.zero_() - self.linear2.weight.data.normal_(mean=0.0, std=0.01) - self.linear2.bias.data.zero_() - - self.to(devices.device) - - def forward(self, x): - return x + (self.linear2(self.linear1(x))) - - -class Hypernetwork: - filename = None - name = None - - def __init__(self, name=None): - self.filename = None - self.name = name - self.layers = {} - self.step = 0 - self.sd_checkpoint = None - self.sd_checkpoint_name = None - - for size in [320, 640, 768, 1280]: - self.layers[size] = (HypernetworkModule(size), HypernetworkModule(size)) - - def weights(self): - res = [] - - for k, layers in self.layers.items(): - for layer in layers: - layer.train() - res += [layer.linear1.weight, layer.linear1.bias, layer.linear2.weight, layer.linear2.bias] - - return res - - def save(self, filename): - state_dict = {} - - for k, v in self.layers.items(): - state_dict[k] = (v[0].state_dict(), v[1].state_dict()) - - state_dict['step'] = self.step - state_dict['name'] = self.name - state_dict['sd_checkpoint'] = self.sd_checkpoint - state_dict['sd_checkpoint_name'] = self.sd_checkpoint_name - - torch.save(state_dict, filename) - - def load(self, filename): - self.filename = filename - if self.name is None: - self.name = os.path.splitext(os.path.basename(filename))[0] - - state_dict = torch.load(filename, map_location='cpu') - - for size, sd in state_dict.items(): - if type(size) == int: - self.layers[size] = (HypernetworkModule(size, sd[0]), HypernetworkModule(size, sd[1])) - - self.name = state_dict.get('name', self.name) - self.step = state_dict.get('step', 0) - self.sd_checkpoint = state_dict.get('sd_checkpoint', None) - self.sd_checkpoint_name = state_dict.get('sd_checkpoint_name', None) - - -def list_hypernetworks(path): - res = {} - for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True): - name = os.path.splitext(os.path.basename(filename))[0] - res[name] = filename - return res - - -def load_hypernetwork(filename): - path = shared.hypernetworks.get(filename, None) - if path is not None: - print(f"Loading hypernetwork {filename}") - try: - shared.loaded_hypernetwork = Hypernetwork() - shared.loaded_hypernetwork.load(path) - - except Exception: - print(f"Error loading hypernetwork {path}", file=sys.stderr) - print(traceback.format_exc(), file=sys.stderr) - else: - if shared.loaded_hypernetwork is not None: - print(f"Unloading hypernetwork") - - shared.loaded_hypernetwork = None - - -def apply_hypernetwork(hypernetwork, context, layer=None): - hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None) - - if hypernetwork_layers is None: - return context, context - - if layer is not None: - layer.hyper_k = hypernetwork_layers[0] - layer.hyper_v = hypernetwork_layers[1] - - context_k = hypernetwork_layers[0](context) - context_v = hypernetwork_layers[1](context) - return context_k, context_v - - -def attention_CrossAttention_forward(self, x, context=None, mask=None): - h = self.heads - - q = self.to_q(x) - context = default(context, x) - - context_k, context_v = apply_hypernetwork(shared.loaded_hypernetwork, context, self) - k = self.to_k(context_k) - v = self.to_v(context_v) - - q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v)) - - sim = einsum('b i d, b j d -> b i j', q, k) * self.scale - - if mask is not None: - mask = rearrange(mask, 'b ... -> b (...)') - max_neg_value = -torch.finfo(sim.dtype).max - mask = repeat(mask, 'b j -> (b h) () j', h=h) - sim.masked_fill_(~mask, max_neg_value) - - # attention, what we cannot get enough of - attn = sim.softmax(dim=-1) - - out = einsum('b i j, b j d -> b i d', attn, v) - out = rearrange(out, '(b h) n d -> b n (h d)', h=h) - return self.to_out(out) - - -def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory, steps, create_image_every, save_hypernetwork_every, template_file, preview_image_prompt): - assert hypernetwork_name, 'embedding not selected' - - path = shared.hypernetworks.get(hypernetwork_name, None) - shared.loaded_hypernetwork = Hypernetwork() - shared.loaded_hypernetwork.load(path) - - shared.state.textinfo = "Initializing hypernetwork training..." - shared.state.job_count = steps - - filename = os.path.join(shared.cmd_opts.hypernetwork_dir, f'{hypernetwork_name}.pt') - - log_directory = os.path.join(log_directory, datetime.datetime.now().strftime("%Y-%m-%d"), hypernetwork_name) - - if save_hypernetwork_every > 0: - hypernetwork_dir = os.path.join(log_directory, "hypernetworks") - os.makedirs(hypernetwork_dir, exist_ok=True) - else: - hypernetwork_dir = None - - if create_image_every > 0: - images_dir = os.path.join(log_directory, "images") - os.makedirs(images_dir, exist_ok=True) - else: - images_dir = None - - cond_model = shared.sd_model.cond_stage_model - - shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..." - with torch.autocast("cuda"): - ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=512, height=512, repeats=1, placeholder_token=hypernetwork_name, model=shared.sd_model, device=devices.device, template_file=template_file) - - hypernetwork = shared.loaded_hypernetwork - weights = hypernetwork.weights() - for weight in weights: - weight.requires_grad = True - - optimizer = torch.optim.AdamW(weights, lr=learn_rate) - - losses = torch.zeros((32,)) - - last_saved_file = "" - last_saved_image = "" - - ititial_step = hypernetwork.step or 0 - if ititial_step > steps: - return hypernetwork, filename - - pbar = tqdm.tqdm(enumerate(ds), total=steps - ititial_step) - for i, (x, text) in pbar: - hypernetwork.step = i + ititial_step - - if hypernetwork.step > steps: - break - - if shared.state.interrupted: - break - - with torch.autocast("cuda"): - c = cond_model([text]) - - x = x.to(devices.device) - loss = shared.sd_model(x.unsqueeze(0), c)[0] - del x - - losses[hypernetwork.step % losses.shape[0]] = loss.item() - - optimizer.zero_grad() - loss.backward() - optimizer.step() - - pbar.set_description(f"loss: {losses.mean():.7f}") - - if hypernetwork.step > 0 and hypernetwork_dir is not None and hypernetwork.step % save_hypernetwork_every == 0: - last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork_name}-{hypernetwork.step}.pt') - hypernetwork.save(last_saved_file) - - if hypernetwork.step > 0 and images_dir is not None and hypernetwork.step % create_image_every == 0: - last_saved_image = os.path.join(images_dir, f'{hypernetwork_name}-{hypernetwork.step}.png') - - preview_text = text if preview_image_prompt == "" else preview_image_prompt - - p = processing.StableDiffusionProcessingTxt2Img( - sd_model=shared.sd_model, - prompt=preview_text, - steps=20, - do_not_save_grid=True, - do_not_save_samples=True, - ) - - processed = processing.process_images(p) - image = processed.images[0] - - shared.state.current_image = image - image.save(last_saved_image) - - last_saved_image += f", prompt: {preview_text}" - - shared.state.job_no = hypernetwork.step - - shared.state.textinfo = f""" -

-Loss: {losses.mean():.7f}
-Step: {hypernetwork.step}
-Last prompt: {html.escape(text)}
-Last saved embedding: {html.escape(last_saved_file)}
-Last saved image: {html.escape(last_saved_image)}
-

-""" - - checkpoint = sd_models.select_checkpoint() - - hypernetwork.sd_checkpoint = checkpoint.hash - hypernetwork.sd_checkpoint_name = checkpoint.model_name - hypernetwork.save(filename) - - return hypernetwork, filename - - diff --git a/modules/hypernetwork/ui.py b/modules/hypernetwork/ui.py deleted file mode 100644 index f6d1d0a3..00000000 --- a/modules/hypernetwork/ui.py +++ /dev/null @@ -1,43 +0,0 @@ -import html -import os - -import gradio as gr - -import modules.textual_inversion.textual_inversion -import modules.textual_inversion.preprocess -from modules import sd_hijack, shared -from modules.hypernetwork import hypernetwork - - -def create_hypernetwork(name): - fn = os.path.join(shared.cmd_opts.hypernetwork_dir, f"{name}.pt") - assert not os.path.exists(fn), f"file {fn} already exists" - - hypernet = modules.hypernetwork.hypernetwork.Hypernetwork(name=name) - hypernet.save(fn) - - shared.reload_hypernetworks() - - return gr.Dropdown.update(choices=sorted([x for x in shared.hypernetworks.keys()])), f"Created: {fn}", "" - - -def train_hypernetwork(*args): - - initial_hypernetwork = shared.loaded_hypernetwork - - try: - sd_hijack.undo_optimizations() - - hypernetwork, filename = modules.hypernetwork.hypernetwork.train_hypernetwork(*args) - - res = f""" -Training {'interrupted' if shared.state.interrupted else 'finished'} at {hypernetwork.step} steps. -Hypernetwork saved to {html.escape(filename)} -""" - return res, "" - except Exception: - raise - finally: - shared.loaded_hypernetwork = initial_hypernetwork - sd_hijack.apply_optimizations() - diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py new file mode 100644 index 00000000..aa701bda --- /dev/null +++ b/modules/hypernetworks/hypernetwork.py @@ -0,0 +1,283 @@ +import datetime +import glob +import html +import os +import sys +import traceback +import tqdm + +import torch + +from ldm.util import default +from modules import devices, shared, processing, sd_models +import torch +from torch import einsum +from einops import rearrange, repeat +import modules.textual_inversion.dataset + + +class HypernetworkModule(torch.nn.Module): + def __init__(self, dim, state_dict=None): + super().__init__() + + self.linear1 = torch.nn.Linear(dim, dim * 2) + self.linear2 = torch.nn.Linear(dim * 2, dim) + + if state_dict is not None: + self.load_state_dict(state_dict, strict=True) + else: + + self.linear1.weight.data.normal_(mean=0.0, std=0.01) + self.linear1.bias.data.zero_() + self.linear2.weight.data.normal_(mean=0.0, std=0.01) + self.linear2.bias.data.zero_() + + self.to(devices.device) + + def forward(self, x): + return x + (self.linear2(self.linear1(x))) + + +class Hypernetwork: + filename = None + name = None + + def __init__(self, name=None): + self.filename = None + self.name = name + self.layers = {} + self.step = 0 + self.sd_checkpoint = None + self.sd_checkpoint_name = None + + for size in [320, 640, 768, 1280]: + self.layers[size] = (HypernetworkModule(size), HypernetworkModule(size)) + + def weights(self): + res = [] + + for k, layers in self.layers.items(): + for layer in layers: + layer.train() + res += [layer.linear1.weight, layer.linear1.bias, layer.linear2.weight, layer.linear2.bias] + + return res + + def save(self, filename): + state_dict = {} + + for k, v in self.layers.items(): + state_dict[k] = (v[0].state_dict(), v[1].state_dict()) + + state_dict['step'] = self.step + state_dict['name'] = self.name + state_dict['sd_checkpoint'] = self.sd_checkpoint + state_dict['sd_checkpoint_name'] = self.sd_checkpoint_name + + torch.save(state_dict, filename) + + def load(self, filename): + self.filename = filename + if self.name is None: + self.name = os.path.splitext(os.path.basename(filename))[0] + + state_dict = torch.load(filename, map_location='cpu') + + for size, sd in state_dict.items(): + if type(size) == int: + self.layers[size] = (HypernetworkModule(size, sd[0]), HypernetworkModule(size, sd[1])) + + self.name = state_dict.get('name', self.name) + self.step = state_dict.get('step', 0) + self.sd_checkpoint = state_dict.get('sd_checkpoint', None) + self.sd_checkpoint_name = state_dict.get('sd_checkpoint_name', None) + + +def list_hypernetworks(path): + res = {} + for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True): + name = os.path.splitext(os.path.basename(filename))[0] + res[name] = filename + return res + + +def load_hypernetwork(filename): + path = shared.hypernetworks.get(filename, None) + if path is not None: + print(f"Loading hypernetwork {filename}") + try: + shared.loaded_hypernetwork = Hypernetwork() + shared.loaded_hypernetwork.load(path) + + except Exception: + print(f"Error loading hypernetwork {path}", file=sys.stderr) + print(traceback.format_exc(), file=sys.stderr) + else: + if shared.loaded_hypernetwork is not None: + print(f"Unloading hypernetwork") + + shared.loaded_hypernetwork = None + + +def apply_hypernetwork(hypernetwork, context, layer=None): + hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None) + + if hypernetwork_layers is None: + return context, context + + if layer is not None: + layer.hyper_k = hypernetwork_layers[0] + layer.hyper_v = hypernetwork_layers[1] + + context_k = hypernetwork_layers[0](context) + context_v = hypernetwork_layers[1](context) + return context_k, context_v + + +def attention_CrossAttention_forward(self, x, context=None, mask=None): + h = self.heads + + q = self.to_q(x) + context = default(context, x) + + context_k, context_v = apply_hypernetwork(shared.loaded_hypernetwork, context, self) + k = self.to_k(context_k) + v = self.to_v(context_v) + + q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v)) + + sim = einsum('b i d, b j d -> b i j', q, k) * self.scale + + if mask is not None: + mask = rearrange(mask, 'b ... -> b (...)') + max_neg_value = -torch.finfo(sim.dtype).max + mask = repeat(mask, 'b j -> (b h) () j', h=h) + sim.masked_fill_(~mask, max_neg_value) + + # attention, what we cannot get enough of + attn = sim.softmax(dim=-1) + + out = einsum('b i j, b j d -> b i d', attn, v) + out = rearrange(out, '(b h) n d -> b n (h d)', h=h) + return self.to_out(out) + + +def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory, steps, create_image_every, save_hypernetwork_every, template_file, preview_image_prompt): + assert hypernetwork_name, 'embedding not selected' + + path = shared.hypernetworks.get(hypernetwork_name, None) + shared.loaded_hypernetwork = Hypernetwork() + shared.loaded_hypernetwork.load(path) + + shared.state.textinfo = "Initializing hypernetwork training..." + shared.state.job_count = steps + + filename = os.path.join(shared.cmd_opts.hypernetwork_dir, f'{hypernetwork_name}.pt') + + log_directory = os.path.join(log_directory, datetime.datetime.now().strftime("%Y-%m-%d"), hypernetwork_name) + + if save_hypernetwork_every > 0: + hypernetwork_dir = os.path.join(log_directory, "hypernetworks") + os.makedirs(hypernetwork_dir, exist_ok=True) + else: + hypernetwork_dir = None + + if create_image_every > 0: + images_dir = os.path.join(log_directory, "images") + os.makedirs(images_dir, exist_ok=True) + else: + images_dir = None + + cond_model = shared.sd_model.cond_stage_model + + shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..." + with torch.autocast("cuda"): + ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=512, height=512, repeats=1, placeholder_token=hypernetwork_name, model=shared.sd_model, device=devices.device, template_file=template_file) + + hypernetwork = shared.loaded_hypernetwork + weights = hypernetwork.weights() + for weight in weights: + weight.requires_grad = True + + optimizer = torch.optim.AdamW(weights, lr=learn_rate) + + losses = torch.zeros((32,)) + + last_saved_file = "" + last_saved_image = "" + + ititial_step = hypernetwork.step or 0 + if ititial_step > steps: + return hypernetwork, filename + + pbar = tqdm.tqdm(enumerate(ds), total=steps - ititial_step) + for i, (x, text) in pbar: + hypernetwork.step = i + ititial_step + + if hypernetwork.step > steps: + break + + if shared.state.interrupted: + break + + with torch.autocast("cuda"): + c = cond_model([text]) + + x = x.to(devices.device) + loss = shared.sd_model(x.unsqueeze(0), c)[0] + del x + + losses[hypernetwork.step % losses.shape[0]] = loss.item() + + optimizer.zero_grad() + loss.backward() + optimizer.step() + + pbar.set_description(f"loss: {losses.mean():.7f}") + + if hypernetwork.step > 0 and hypernetwork_dir is not None and hypernetwork.step % save_hypernetwork_every == 0: + last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork_name}-{hypernetwork.step}.pt') + hypernetwork.save(last_saved_file) + + if hypernetwork.step > 0 and images_dir is not None and hypernetwork.step % create_image_every == 0: + last_saved_image = os.path.join(images_dir, f'{hypernetwork_name}-{hypernetwork.step}.png') + + preview_text = text if preview_image_prompt == "" else preview_image_prompt + + p = processing.StableDiffusionProcessingTxt2Img( + sd_model=shared.sd_model, + prompt=preview_text, + steps=20, + do_not_save_grid=True, + do_not_save_samples=True, + ) + + processed = processing.process_images(p) + image = processed.images[0] + + shared.state.current_image = image + image.save(last_saved_image) + + last_saved_image += f", prompt: {preview_text}" + + shared.state.job_no = hypernetwork.step + + shared.state.textinfo = f""" +

+Loss: {losses.mean():.7f}
+Step: {hypernetwork.step}
+Last prompt: {html.escape(text)}
+Last saved embedding: {html.escape(last_saved_file)}
+Last saved image: {html.escape(last_saved_image)}
+

+""" + + checkpoint = sd_models.select_checkpoint() + + hypernetwork.sd_checkpoint = checkpoint.hash + hypernetwork.sd_checkpoint_name = checkpoint.model_name + hypernetwork.save(filename) + + return hypernetwork, filename + + diff --git a/modules/hypernetworks/ui.py b/modules/hypernetworks/ui.py new file mode 100644 index 00000000..811bc31e --- /dev/null +++ b/modules/hypernetworks/ui.py @@ -0,0 +1,43 @@ +import html +import os + +import gradio as gr + +import modules.textual_inversion.textual_inversion +import modules.textual_inversion.preprocess +from modules import sd_hijack, shared +from modules.hypernetworks import hypernetwork + + +def create_hypernetwork(name): + fn = os.path.join(shared.cmd_opts.hypernetwork_dir, f"{name}.pt") + assert not os.path.exists(fn), f"file {fn} already exists" + + hypernet = modules.hypernetwork.hypernetwork.Hypernetwork(name=name) + hypernet.save(fn) + + shared.reload_hypernetworks() + + return gr.Dropdown.update(choices=sorted([x for x in shared.hypernetworks.keys()])), f"Created: {fn}", "" + + +def train_hypernetwork(*args): + + initial_hypernetwork = shared.loaded_hypernetwork + + try: + sd_hijack.undo_optimizations() + + hypernetwork, filename = modules.hypernetwork.hypernetwork.train_hypernetwork(*args) + + res = f""" +Training {'interrupted' if shared.state.interrupted else 'finished'} at {hypernetwork.step} steps. +Hypernetwork saved to {html.escape(filename)} +""" + return res, "" + except Exception: + raise + finally: + shared.loaded_hypernetwork = initial_hypernetwork + sd_hijack.apply_optimizations() + diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index f873049a..f07ec041 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -37,7 +37,7 @@ def apply_optimizations(): def undo_optimizations(): - from modules.hypernetwork import hypernetwork + from modules.hypernetworks import hypernetwork ldm.modules.attention.CrossAttention.forward = hypernetwork.attention_CrossAttention_forward ldm.modules.diffusionmodules.model.nonlinearity = diffusionmodules_model_nonlinearity diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py index 27e571fc..3349b9c3 100644 --- a/modules/sd_hijack_optimizations.py +++ b/modules/sd_hijack_optimizations.py @@ -9,7 +9,7 @@ from ldm.util import default from einops import rearrange from modules import shared -from modules.hypernetwork import hypernetwork +from modules.hypernetworks import hypernetwork if shared.cmd_opts.xformers or shared.cmd_opts.force_enable_xformers: diff --git a/modules/shared.py b/modules/shared.py index 375e3afb..1dc2ccf2 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -14,7 +14,7 @@ import modules.sd_models import modules.styles import modules.devices as devices from modules import sd_samplers -from modules.hypernetwork import hypernetwork +from modules.hypernetworks import hypernetwork from modules.paths import models_path, script_path, sd_path sd_model_file = os.path.join(script_path, 'model.ckpt') diff --git a/modules/ui.py b/modules/ui.py index f57f32db..42e5d866 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -39,7 +39,7 @@ import modules.generation_parameters_copypaste from modules import prompt_parser from modules.images import save_image import modules.textual_inversion.ui -import modules.hypernetwork.ui +import modules.hypernetworks.ui # this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the browser will not show any UI mimetypes.init() diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py index 16918c99..cddb192a 100644 --- a/scripts/xy_grid.py +++ b/scripts/xy_grid.py @@ -11,7 +11,7 @@ import modules.scripts as scripts import gradio as gr from modules import images -from modules.hypernetwork import hypernetwork +from modules.hypernetworks import hypernetwork from modules.processing import process_images, Processed, get_correct_sampler from modules.shared import opts, cmd_opts, state import modules.shared as shared diff --git a/webui.py b/webui.py index ba2156c8..faa38a0d 100644 --- a/webui.py +++ b/webui.py @@ -29,7 +29,7 @@ from modules import devices from modules import modelloader from modules.paths import script_path from modules.shared import cmd_opts -import modules.hypernetwork.hypernetwork +import modules.hypernetworks.hypernetwork modelloader.cleanup_models() modules.sd_models.setup_model() -- cgit v1.2.3