Merge remote-tracking branch 'upstream/master' into token_count

2 files changed, 73 insertions, 8 deletions

diff --git a/scripts/img2imgalt.py b/scripts/img2imgalt.py
index 7b4ba244..0ef137f7 100644
--- a/scripts/img2imgalt.py
+++ b/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)

-                self.cache = Cached(rec_noise, cfg, st, lat, original_prompt, original_negative_prompt)

+                if sigma_adjustment:

+                    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)

 

diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py
index 3a2e103f..7c01231f 100644
--- a/scripts/xy_grid.py
+++ b/scripts/xy_grid.py
@@ -2,6 +2,7 @@ from collections import namedtuple
 from copy import copy

 import random

 

+from PIL import Image

 import numpy as np

 

 import modules.scripts as scripts

@@ -86,7 +87,12 @@ axis_options = [
     AxisOption("Prompt S/R", str, apply_prompt, format_value),

     AxisOption("Sampler", str, apply_sampler, format_value),

     AxisOption("Checkpoint name", str, apply_checkpoint, format_value),

-    AxisOptionImg2Img("Denoising", float, apply_field("denoising_strength"), format_value_add_label), #  as it is now all AxisOptionImg2Img items must go after AxisOption ones

+    AxisOption("Sigma Churn", float, apply_field("s_churn"),  format_value_add_label),

+    AxisOption("Sigma min",   float, apply_field("s_tmin"),   format_value_add_label),

+    AxisOption("Sigma max",   float, apply_field("s_tmax"),   format_value_add_label),

+    AxisOption("Sigma noise", float, apply_field("s_noise"),  format_value_add_label),

+    AxisOption("DDIM Eta",    float, apply_field("ddim_eta"), format_value_add_label),

+    AxisOptionImg2Img("Denoising", float, apply_field("denoising_strength"), format_value_add_label),#  as it is now all AxisOptionImg2Img items must go after AxisOption ones

 ]

 

 

@@ -108,7 +114,10 @@ def draw_xy_grid(p, xs, ys, x_labels, y_labels, cell, draw_legend):
             if first_pocessed is None:

                 first_pocessed = processed

 

-            res.append(processed.images[0])

+            try:

+              res.append(processed.images[0])

+            except:

+              res.append(Image.new(res[0].mode, res[0].size))

 

     grid = images.image_grid(res, rows=len(ys))

     if draw_legend: