apextoaster
/
onnx-web
1
0
Fork 0
Code Actions

handle panorama margins for img2img and inpaint

This commit is contained in:
Sean Sube 2023-12-03 06:28:36 -06:00
parent 16911b5f87
commit c42ca9ca38
Signed by: ssube
GPG Key ID: 3EED7B957D362AF1
2 changed files with 39 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
api/onnx_web/diffusers/pipelines/panorama.py
View File

@ -566,6 +566,7 @@ class OnnxStableDiffusionPanoramaPipeline(DiffusionPipeline):
count = np.zeros((latents.shape[0], latents.shape[1], *resize))
value = np.zeros((latents.shape[0], latents.shape[1], *resize))
# adjust latents
latents = expand_latents(
latents,
generator.randint(np.iinfo(np.int32).max),
@ -974,8 +975,16 @@ class OnnxStableDiffusionPanoramaPipeline(DiffusionPipeline):
# panorama additions
views, resize = self.get_views(height, width, self.window, self.stride)
count = np.zeros_like(latents)
value = np.zeros_like(latents)
count = np.zeros((latents.shape[0], latents.shape[1], *resize))
value = np.zeros((latents.shape[0], latents.shape[1], *resize))
# adjust latents
latents = expand_latents(
latents,
generator.randint(np.iinfo(np.int32).max),
Size(resize[1], resize[0]),
sigma=self.scheduler.init_noise_sigma,
)
for i, t in enumerate(self.progress_bar(timesteps)):
count.fill(0)
@ -1031,6 +1040,9 @@ class OnnxStableDiffusionPanoramaPipeline(DiffusionPipeline):
if callback is not None and i % callback_steps == 0:
callback(i, t, latents)
# remove extra margins
latents = latents[:, :, 0:(height // 8), 0:(width // 8)]
latents = 1 / 0.18215 * latents
# image = self.vae_decoder(latent_sample=latents)[0]
# it seems likes there is a strange result for using half-precision vae decoder if batchsize>1
@ -1282,8 +1294,16 @@ class OnnxStableDiffusionPanoramaPipeline(DiffusionPipeline):
# panorama additions
views, resize = self.get_views(height, width, self.window, self.stride)
count = np.zeros_like(latents)
value = np.zeros_like(latents)
count = np.zeros((latents.shape[0], latents.shape[1], *resize))
value = np.zeros((latents.shape[0], latents.shape[1], *resize))
# adjust latents
latents = expand_latents(
latents,
generator.randint(np.iinfo(np.int32).max),
Size(resize[1], resize[0]),
sigma=self.scheduler.init_noise_sigma,
)
for i, t in enumerate(self.progress_bar(self.scheduler.timesteps)):
count.fill(0)
@ -1346,6 +1366,9 @@ class OnnxStableDiffusionPanoramaPipeline(DiffusionPipeline):
if callback is not None and i % callback_steps == 0:
callback(i, t, latents)
# remove extra margins
latents = latents[:, :, 0:(height // 8), 0:(width // 8)]
latents = 1 / 0.18215 * latents
# image = self.vae_decoder(latent_sample=latents)[0]
# it seems likes there is a strange result for using half-precision vae decoder if batchsize>1

14
api/onnx_web/diffusers/pipelines/panorama_xl.py
View File

@ -810,8 +810,15 @@ class StableDiffusionXLPanoramaPipelineMixin(StableDiffusionXLImg2ImgPipelineMix
# 8. Panorama additions
views, resize = self.get_views(height, width, self.window, self.stride)
count = np.zeros_like(latents)
value = np.zeros_like(latents)
count = np.zeros((latents.shape[0], latents.shape[1], *resize))
value = np.zeros((latents.shape[0], latents.shape[1], *resize))
latents = expand_latents(
latents,
generator.randint(np.iinfo(np.int32).max),
Size(resize[1], resize[0]),
sigma=self.scheduler.init_noise_sigma,
)
# 8. Denoising loop
num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
@ -881,6 +888,9 @@ class StableDiffusionXLPanoramaPipelineMixin(StableDiffusionXLImg2ImgPipelineMix
if callback is not None and i % callback_steps == 0:
callback(i, t, latents)
# remove extra margins
latents = latents[:, :, 0:(height // 8), 0:(width // 8)]
if output_type == "latent":
image = latents
else: