Skip to content

[chore] fix-copies to flux pipelines #10941

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 3, 2025
Merged

[chore] fix-copies to flux pipelines #10941

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 12 additions & 7 deletions src/diffusers/pipelines/flux/pipeline_flux_controlnet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -440,23 +440,28 @@ def prepare_ip_adapter_image_embeds(
if not isinstance(ip_adapter_image, list):
ip_adapter_image = [ip_adapter_image]

if len(ip_adapter_image) != len(self.transformer.encoder_hid_proj.image_projection_layers):
if len(ip_adapter_image) != self.transformer.encoder_hid_proj.num_ip_adapters:
raise ValueError(
f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(self.transformer.encoder_hid_proj.image_projection_layers)} IP Adapters."
f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {self.transformer.encoder_hid_proj.num_ip_adapters} IP Adapters."
)

for single_ip_adapter_image, image_proj_layer in zip(
ip_adapter_image, self.transformer.encoder_hid_proj.image_projection_layers
):
for single_ip_adapter_image in ip_adapter_image:
single_image_embeds = self.encode_image(single_ip_adapter_image, device, 1)

image_embeds.append(single_image_embeds[None, :])
else:
if not isinstance(ip_adapter_image_embeds, list):
ip_adapter_image_embeds = [ip_adapter_image_embeds]

if len(ip_adapter_image_embeds) != self.transformer.encoder_hid_proj.num_ip_adapters:
raise ValueError(
f"`ip_adapter_image_embeds` must have same length as the number of IP Adapters. Got {len(ip_adapter_image_embeds)} image embeds and {self.transformer.encoder_hid_proj.num_ip_adapters} IP Adapters."
)

for single_image_embeds in ip_adapter_image_embeds:
image_embeds.append(single_image_embeds)

ip_adapter_image_embeds = []
for i, single_image_embeds in enumerate(image_embeds):
for single_image_embeds in image_embeds:
single_image_embeds = torch.cat([single_image_embeds] * num_images_per_prompt, dim=0)
single_image_embeds = single_image_embeds.to(device=device)
ip_adapter_image_embeds.append(single_image_embeds)
Expand Down
19 changes: 12 additions & 7 deletions src/diffusers/pipelines/flux/pipeline_flux_img2img.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -427,23 +427,28 @@ def prepare_ip_adapter_image_embeds(
if not isinstance(ip_adapter_image, list):
ip_adapter_image = [ip_adapter_image]

if len(ip_adapter_image) != len(self.transformer.encoder_hid_proj.image_projection_layers):
if len(ip_adapter_image) != self.transformer.encoder_hid_proj.num_ip_adapters:
raise ValueError(
f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(self.transformer.encoder_hid_proj.image_projection_layers)} IP Adapters."
f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {self.transformer.encoder_hid_proj.num_ip_adapters} IP Adapters."
)

for single_ip_adapter_image, image_proj_layer in zip(
ip_adapter_image, self.transformer.encoder_hid_proj.image_projection_layers
):
for single_ip_adapter_image in ip_adapter_image:
single_image_embeds = self.encode_image(single_ip_adapter_image, device, 1)

image_embeds.append(single_image_embeds[None, :])
else:
if not isinstance(ip_adapter_image_embeds, list):
ip_adapter_image_embeds = [ip_adapter_image_embeds]

if len(ip_adapter_image_embeds) != self.transformer.encoder_hid_proj.num_ip_adapters:
raise ValueError(
f"`ip_adapter_image_embeds` must have same length as the number of IP Adapters. Got {len(ip_adapter_image_embeds)} image embeds and {self.transformer.encoder_hid_proj.num_ip_adapters} IP Adapters."
)

for single_image_embeds in ip_adapter_image_embeds:
image_embeds.append(single_image_embeds)

ip_adapter_image_embeds = []
for i, single_image_embeds in enumerate(image_embeds):
for single_image_embeds in image_embeds:
single_image_embeds = torch.cat([single_image_embeds] * num_images_per_prompt, dim=0)
single_image_embeds = single_image_embeds.to(device=device)
ip_adapter_image_embeds.append(single_image_embeds)
Expand Down
19 changes: 12 additions & 7 deletions src/diffusers/pipelines/flux/pipeline_flux_inpaint.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -432,23 +432,28 @@ def prepare_ip_adapter_image_embeds(
if not isinstance(ip_adapter_image, list):
ip_adapter_image = [ip_adapter_image]

if len(ip_adapter_image) != len(self.transformer.encoder_hid_proj.image_projection_layers):
if len(ip_adapter_image) != self.transformer.encoder_hid_proj.num_ip_adapters:
raise ValueError(
f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(self.transformer.encoder_hid_proj.image_projection_layers)} IP Adapters."
f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {self.transformer.encoder_hid_proj.num_ip_adapters} IP Adapters."
)

for single_ip_adapter_image, image_proj_layer in zip(
ip_adapter_image, self.transformer.encoder_hid_proj.image_projection_layers
):
for single_ip_adapter_image in ip_adapter_image:
single_image_embeds = self.encode_image(single_ip_adapter_image, device, 1)

image_embeds.append(single_image_embeds[None, :])
else:
if not isinstance(ip_adapter_image_embeds, list):
ip_adapter_image_embeds = [ip_adapter_image_embeds]

if len(ip_adapter_image_embeds) != self.transformer.encoder_hid_proj.num_ip_adapters:
raise ValueError(
f"`ip_adapter_image_embeds` must have same length as the number of IP Adapters. Got {len(ip_adapter_image_embeds)} image embeds and {self.transformer.encoder_hid_proj.num_ip_adapters} IP Adapters."
)

for single_image_embeds in ip_adapter_image_embeds:
image_embeds.append(single_image_embeds)

ip_adapter_image_embeds = []
for i, single_image_embeds in enumerate(image_embeds):
for single_image_embeds in image_embeds:
single_image_embeds = torch.cat([single_image_embeds] * num_images_per_prompt, dim=0)
single_image_embeds = single_image_embeds.to(device=device)
ip_adapter_image_embeds.append(single_image_embeds)
Expand Down