Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/main' into fix/hires_inpaint

Browse Source
This commit is contained in:
Kevin Turner 2023-01-29 10:51:59 -08:00
commit 5a8c28de97
1 changed files with 22 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
ldm/invoke/generator/txt2img2img.py
View File

@ -38,10 +38,6 @@ class Txt2Img2Img(Generator):
uc, c, cfg_scale, extra_conditioning_info, uc, c, cfg_scale, extra_conditioning_info,
threshold = ThresholdSettings(threshold, warmup=0.2) if threshold else None) threshold = ThresholdSettings(threshold, warmup=0.2) if threshold else None)
.add_scheduler_args_if_applicable(pipeline.scheduler, eta=ddim_eta)) .add_scheduler_args_if_applicable(pipeline.scheduler, eta=ddim_eta))
scale_dim = min(width, height)
scale = 512 / scale_dim
init_width, init_height = trim_to_multiple_of(scale * width, scale * height)
def make_image(x_T): def make_image(x_T):
@ -54,6 +50,10 @@ class Txt2Img2Img(Generator):
# TODO: threshold = threshold, # TODO: threshold = threshold,
) )
# Get our initial generation width and height directly from the latent output so
# the message below is accurate.
init_width = first_pass_latent_output.size()[3] * self.downsampling_factor
init_height = first_pass_latent_output.size()[2] * self.downsampling_factor
print( print(
f"\n>> Interpolating from {init_width}x{init_height} to {width}x{height} using DDIM sampling" f"\n>> Interpolating from {init_width}x{init_height} to {width}x{height} using DDIM sampling"
) )
@ -106,11 +106,24 @@ class Txt2Img2Img(Generator):
def get_noise(self,width,height,scale = True): def get_noise(self,width,height,scale = True):
# print(f"Get noise: {width}x{height}") # print(f"Get noise: {width}x{height}")
if scale: if scale:
trained_square = 512 * 512 # Scale the input width and height for the initial generation
actual_square = width * height # Make their area equivalent to the model's resolution area (e.g. 512*512 = 262144),
scale = math.sqrt(trained_square / actual_square) # while keeping the minimum dimension at least 0.5 * resolution (e.g. 512*0.5 = 256)
scaled_width = math.ceil(scale * width / 64) * 64
scaled_height = math.ceil(scale * height / 64) * 64 aspect = width / height
dimension = self.model.unet.config.sample_size * self.model.vae_scale_factor
min_dimension = math.floor(dimension * 0.5)
model_area = dimension * dimension # hardcoded for now since all models are trained on square images
if aspect > 1.0:
init_height = max(min_dimension, math.sqrt(model_area / aspect))
init_width = init_height * aspect
else:
init_width = max(min_dimension, math.sqrt(model_area * aspect))
init_height = init_width / aspect
scaled_width, scaled_height = trim_to_multiple_of(math.floor(init_width), math.floor(init_height))
else: else:
scaled_width = width scaled_width = width
scaled_height = height scaled_height = height