Merge branch 'master' into notification-sound

.gitignore

@@ -21,3 +21,4 @@ __pycache__
 /user.css
 /.idea
 notification.mp3
+/SwinIR

javascript/dragdrop.js

@@ -68,13 +68,19 @@ window.addEventListener('paste', e => {
     if ( ! isValidImageList( files ) ) {
         return;
     }
-    [...gradioApp().querySelectorAll('input[type=file][accept="image/x-png,image/gif,image/jpeg"]')]
+
-        .filter(input => !input.matches('.\\!hidden input[type=file]'))
+    const visibleImageFields = [...gradioApp().querySelectorAll('[data-testid="image"]')]
-        .forEach(input => {
+        .filter(el => uiElementIsVisible(el));
-            input.files = files;
+    if ( ! visibleImageFields.length ) {
-            input.dispatchEvent(new Event('change'))
+        return;
-        });
+    }
-    [...gradioApp().querySelectorAll('[data-testid="image"]')]
+    
-        .filter(imgWrap => !imgWrap.closest('.\\!hidden'))
+    const firstFreeImageField = visibleImageFields
-        .forEach(imgWrap => dropReplaceImage( imgWrap, files ));
+        .filter(el => el.querySelector('input[type=file]'))?.[0];
+
+    dropReplaceImage(
+        firstFreeImageField ?
+        firstFreeImageField :
+        visibleImageFields[visibleImageFields.length - 1]
+    , files );
 });

javascript/ui.js

@@ -1,9 +1,8 @@
 // various functions for interation with ui.py not large enough to warrant putting them in separate files
 
 function selected_gallery_index(){
-    var gr = gradioApp()
+    var buttons = gradioApp().querySelectorAll('[style="display: block;"].tabitem .gallery-item')
-    var buttons = gradioApp().querySelectorAll(".gallery-item")
+    var button = gradioApp().querySelector('[style="display: block;"].tabitem .gallery-item.\\!ring-2')
-    var button = gr.querySelector(".gallery-item.\\!ring-2")
 
     var result = -1
     buttons.forEach(function(v, i){ if(v==button) { result = i } })

modules/processing.py

@@ -406,7 +406,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
                 index_of_first_image = 1
 
             if opts.grid_save:
-                images.save_image(grid, p.outpath_grids, "grid", all_seeds[0], all_prompts[0], opts.grid_format, info=infotext(), short_filename=not opts.grid_extended_filename, p=p)
+                images.save_image(grid, p.outpath_grids, "grid", all_seeds[0], all_prompts[0], opts.grid_format, info=infotext(), short_filename=not opts.grid_extended_filename, p=p, grid=True)
 
     devices.torch_gc()
     return Processed(p, output_images, all_seeds[0], infotext(), subseed=all_subseeds[0], all_prompts=all_prompts, all_seeds=all_seeds, all_subseeds=all_subseeds, index_of_first_image=index_of_first_image)

modules/shared.py

@@ -66,7 +66,7 @@ class State:
     job = ""
     job_no = 0
     job_count = 0
-    job_timestamp = 0
+    job_timestamp = '0'
     sampling_step = 0
     sampling_steps = 0
     current_latent = None
@@ -80,6 +80,7 @@ class State:
         self.job_no += 1
         self.sampling_step = 0
         self.current_image_sampling_step = 0
+        
     def get_job_timestamp(self):
         return datetime.datetime.now().strftime("%Y%m%d%H%M%S")
 

script.js

@@ -39,3 +39,24 @@ document.addEventListener("DOMContentLoaded", function() {
     });
     mutationObserver.observe( gradioApp(), { childList:true, subtree:true })
 });
+
+/**
+ * checks that a UI element is not in another hidden element or tab content
+ */
+function uiElementIsVisible(el) {
+    let isVisible = !el.closest('.\\!hidden');
+    if ( ! isVisible ) {
+        return false;
+    }
+
+    while( isVisible = el.closest('.tabitem')?.style.display !== 'none' ) {
+        if ( ! isVisible ) {
+            return false;
+        } else if ( el.parentElement ) {
+            el = el.parentElement
+        } else {
+            break;
+        }
+    }
+    return isVisible;
+}

scripts/img2imgalt.py

@@ -59,7 +59,55 @@ def find_noise_for_image(p, cond, uncond, cfg_scale, steps):
     return x / x.std()
 
 
-Cached = namedtuple("Cached", ["noise", "cfg_scale", "steps", "latent", "original_prompt", "original_negative_prompt"])
+Cached = namedtuple("Cached", ["noise", "cfg_scale", "steps", "latent", "original_prompt", "original_negative_prompt", "sigma_adjustment"])
+
+
+# Based on changes suggested by briansemrau in https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/736
+def find_noise_for_image_sigma_adjustment(p, cond, uncond, cfg_scale, steps):
+    x = p.init_latent
+
+    s_in = x.new_ones([x.shape[0]])
+    dnw = K.external.CompVisDenoiser(shared.sd_model)
+    sigmas = dnw.get_sigmas(steps).flip(0)
+
+    shared.state.sampling_steps = steps
+
+    for i in trange(1, len(sigmas)):
+        shared.state.sampling_step += 1
+
+        x_in = torch.cat([x] * 2)
+        sigma_in = torch.cat([sigmas[i - 1] * s_in] * 2)
+        cond_in = torch.cat([uncond, cond])
+
+        c_out, c_in = [K.utils.append_dims(k, x_in.ndim) for k in dnw.get_scalings(sigma_in)]
+
+        if i == 1:
+            t = dnw.sigma_to_t(torch.cat([sigmas[i] * s_in] * 2))
+        else:
+            t = dnw.sigma_to_t(sigma_in)
+
+        eps = shared.sd_model.apply_model(x_in * c_in, t, cond=cond_in)
+        denoised_uncond, denoised_cond = (x_in + eps * c_out).chunk(2)
+
+        denoised = denoised_uncond + (denoised_cond - denoised_uncond) * cfg_scale
+
+        if i == 1:
+            d = (x - denoised) / (2 * sigmas[i])
+        else:
+            d = (x - denoised) / sigmas[i - 1]
+
+        dt = sigmas[i] - sigmas[i - 1]
+        x = x + d * dt
+
+        sd_samplers.store_latent(x)
+
+        # This shouldn't be necessary, but solved some VRAM issues
+        del x_in, sigma_in, cond_in, c_out, c_in, t,
+        del eps, denoised_uncond, denoised_cond, denoised, d, dt
+
+    shared.state.nextjob()
+
+    return x / sigmas[-1]
 
 
 class Script(scripts.Script):
@@ -78,9 +126,10 @@ class Script(scripts.Script):
         cfg = gr.Slider(label="Decode CFG scale", minimum=0.0, maximum=15.0, step=0.1, value=1.0)
         st = gr.Slider(label="Decode steps", minimum=1, maximum=150, step=1, value=50)
         randomness = gr.Slider(label="Randomness", minimum=0.0, maximum=1.0, step=0.01, value=0.0)
-        return [original_prompt, original_negative_prompt, cfg, st, randomness]
+        sigma_adjustment = gr.Checkbox(label="Sigma adjustment for finding noise for image", value=False)
+        return [original_prompt, original_negative_prompt, cfg, st, randomness, sigma_adjustment]
 
-    def run(self, p, original_prompt, original_negative_prompt, cfg, st, randomness):
+    def run(self, p, original_prompt, original_negative_prompt, cfg, st, randomness, sigma_adjustment):
         p.batch_size = 1
         p.batch_count = 1
 
@@ -88,7 +137,10 @@ class Script(scripts.Script):
         def sample_extra(conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength):
             lat = (p.init_latent.cpu().numpy() * 10).astype(int)
 
-            same_params = self.cache is not None and self.cache.cfg_scale == cfg and self.cache.steps == st and self.cache.original_prompt == original_prompt and self.cache.original_negative_prompt == original_negative_prompt
+            same_params = self.cache is not None and self.cache.cfg_scale == cfg and self.cache.steps == st \
+                                and self.cache.original_prompt == original_prompt \
+                                and self.cache.original_negative_prompt == original_negative_prompt \
+                                and self.cache.sigma_adjustment == sigma_adjustment
             same_everything = same_params and self.cache.latent.shape == lat.shape and np.abs(self.cache.latent-lat).sum() < 100
 
             if same_everything:
@@ -97,8 +149,11 @@ class Script(scripts.Script):
                 shared.state.job_count += 1
                 cond = p.sd_model.get_learned_conditioning(p.batch_size * [original_prompt])
                 uncond = p.sd_model.get_learned_conditioning(p.batch_size * [original_negative_prompt])
-                rec_noise = find_noise_for_image(p, cond, uncond, cfg, st)
+                if sigma_adjustment:
-                self.cache = Cached(rec_noise, cfg, st, lat, original_prompt, original_negative_prompt)
+                    rec_noise = find_noise_for_image_sigma_adjustment(p, cond, uncond, cfg, st)
+                else:
+                    rec_noise = find_noise_for_image(p, cond, uncond, cfg, st)
+                self.cache = Cached(rec_noise, cfg, st, lat, original_prompt, original_negative_prompt, sigma_adjustment)
 
             rand_noise = processing.create_random_tensors(p.init_latent.shape[1:], [p.seed + x + 1 for x in range(p.init_latent.shape[0])])
             
@@ -121,6 +176,7 @@ class Script(scripts.Script):
         p.extra_generation_params["Decode CFG scale"] = cfg
         p.extra_generation_params["Decode steps"] = st
         p.extra_generation_params["Randomness"] = randomness
+        p.extra_generation_params["Sigma Adjustment"] = sigma_adjustment
 
         processed = processing.process_images(p)