Update xy_grid.py

Before a new batch would use the last image from the previous batch. Now
each batch will use the original image for the init image at the start of the
batch.

javascript/contextMenus.js

@@ -147,10 +147,6 @@ generateOnRepeatId = appendContextMenuOption('#txt2img_generate','Generate forev
 
 cancelGenerateForever = function(){ 
   clearInterval(window.generateOnRepeatInterval) 
-  let interruptbutton = gradioApp().querySelector('#txt2img_interrupt');
-  if(interruptbutton.offsetParent){
-      interruptbutton.click();
-  }
 }
 
 appendContextMenuOption('#txt2img_interrupt','Cancel generate forever',cancelGenerateForever)

modules/hypernetwork.py

@@ -64,21 +64,26 @@ def load_hypernetwork(filename):
         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)
 
-    hypernetwork = shared.loaded_hypernetwork
-    hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
-
-    if hypernetwork_layers is not None:
-        k = self.to_k(hypernetwork_layers[0](context))
-        v = self.to_v(hypernetwork_layers[1](context))
-    else:
-        k = self.to_k(context)
-        v = self.to_v(context)
+    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))
 

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 == ',</w>'][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 = []

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
+from modules import shared, hypernetwork
+
 
 if shared.cmd_opts.xformers or shared.cmd_opts.force_enable_xformers:
     try:
@@ -26,16 +27,10 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None):
     q_in = self.to_q(x)
     context = default(context, x)
 
-    hypernetwork = shared.loaded_hypernetwork
-    hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
-
-    if hypernetwork_layers is not None:
-        k_in = self.to_k(hypernetwork_layers[0](context))
-        v_in = self.to_v(hypernetwork_layers[1](context))
-    else:
-        k_in = self.to_k(context)
-        v_in = self.to_v(context)
-    del context, x
+    context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context)
+    k_in = self.to_k(context_k)
+    v_in = self.to_v(context_v)
+    del context, context_k, context_v, x
 
     q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q_in, k_in, v_in))
     del q_in, k_in, v_in
@@ -59,22 +54,16 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None):
     return self.to_out(r2)
 
 
-# taken from https://github.com/Doggettx/stable-diffusion
+# taken from https://github.com/Doggettx/stable-diffusion and modified
 def split_cross_attention_forward(self, x, context=None, mask=None):
     h = self.heads
 
     q_in = self.to_q(x)
     context = default(context, x)
 
-    hypernetwork = shared.loaded_hypernetwork
-    hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
-
-    if hypernetwork_layers is not None:
-        k_in = self.to_k(hypernetwork_layers[0](context))
-        v_in = self.to_v(hypernetwork_layers[1](context))
-    else:
-        k_in = self.to_k(context)
-        v_in = self.to_v(context)
+    context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context)
+    k_in = self.to_k(context_k)
+    v_in = self.to_v(context_v)
 
     k_in *= self.scale
 
@@ -130,14 +119,11 @@ def xformers_attention_forward(self, x, context=None, mask=None):
     h = self.heads
     q_in = self.to_q(x)
     context = default(context, x)
-    hypernetwork = shared.loaded_hypernetwork
-    hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
-    if hypernetwork_layers is not None:
-        k_in = self.to_k(hypernetwork_layers[0](context))
-        v_in = self.to_v(hypernetwork_layers[1](context))
-    else:
-        k_in = self.to_k(context)
-        v_in = self.to_v(context)
+
+    context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context)
+    k_in = self.to_k(context_k)
+    v_in = self.to_v(context_v)
+
     q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b n h d', h=h), (q_in, k_in, v_in))
     del q_in, k_in, v_in
     out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None)

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()}),
@@ -239,6 +240,7 @@ 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"), {

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
 
 
@@ -1331,7 +1331,7 @@ Requested path was: {f}
         
         with gr.Tabs() as tabs:
             for interface, label, ifid in interfaces:
-                with gr.TabItem(label, id=ifid):
+                with gr.TabItem(label, id=ifid, elem_id='tab_' + ifid):
                     interface.render()
         
         if os.path.exists(os.path.join(script_path, "notification.mp3")):

script.js

@@ -6,6 +6,10 @@ function get_uiCurrentTab() {
     return gradioApp().querySelector('.tabs button:not(.border-transparent)')
 }
 
+function get_uiCurrentTabContent() {
+    return gradioApp().querySelector('.tabitem[id^=tab_]:not([style*="display: none"])')
+}
+
 uiUpdateCallbacks = []
 uiTabChangeCallbacks = []
 let uiCurrentTab = null
@@ -50,8 +54,11 @@ document.addEventListener("DOMContentLoaded", function() {
     } else if (e.keyCode !== undefined) {
         if((e.keyCode == 13 && (e.metaKey || e.ctrlKey))) handled = true;
     }
-    if (handled) { 
-        gradioApp().querySelector("#txt2img_generate").click(); 
+    if (handled) {
+        button = get_uiCurrentTabContent().querySelector('button[id$=_generate]');
+        if (button) {
+            button.click();
+        }
         e.preventDefault();
     }
 })

scripts/loopback.py

@@ -38,6 +38,7 @@ class Script(scripts.Script):
 
         grids = []
         all_images = []
+        original_init_image = p.init_images
         state.job_count = loops * batch_count
 
         initial_color_corrections = [processing.setup_color_correction(p.init_images[0])]
@@ -45,6 +46,9 @@ class Script(scripts.Script):
         for n in range(batch_count):
             history = []
 
+            # Reset to original init image at the start of each batch
+            p.init_images = original_init_image
+
             for i in range(loops):
                 p.n_iter = 1
                 p.batch_size = 1

scripts/xy_grid.py

@@ -27,9 +27,17 @@ def apply_field(field):
 
 
 def apply_prompt(p, x, xs):
+
+    orig_prompt = p.prompt
+    orig_negative_prompt = p.negative_prompt
+
     p.prompt = p.prompt.replace(xs[0], x)
     p.negative_prompt = p.negative_prompt.replace(xs[0], x)
 
+    if p.prompt == orig_prompt and p.negative_prompt == orig_negative_prompt:
+        pass
+        #raise RuntimeError(f"Prompt S/R did not find {xs[0]} in prompt or negative prompt. Did you forget to add the token?")
+
 
 def apply_order(p, x, xs):
     token_order = []