Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

Fix some issues with --gpu-only

comfyanonymous7f4725f6b3f7
diff --git a/comfy_extras/nodes_post_processing.py b/comfy_extras/nodes_post_processing.py
index 71660f8a5..cb5c7d228 100644
--- a/comfy_extras/nodes_post_processing.py
+++ b/comfy_extras/nodes_post_processing.py
@@ -33,6 +33,7 @@ class Blend:
CATEGORY = "image/postprocessing"
def blend_images(self, image1: torch.Tensor, image2: torch.Tensor, blend_factor: float, blend_mode: str):
+ image2 = image2.to(image1.device)
if image1.shape != image2.shape:
image2 = image2.permute(0, 3, 1, 2)
image2 = comfy.utils.common_upscale(image2, image1.shape[2], image1.shape[1], upscale_method='bicubic', crop='center')
diff --git a/comfy_extras/nodes_stable3d.py b/comfy_extras/nodes_stable3d.py
index e02a9875a..4375d8f96 100644
--- a/comfy_extras/nodes_stable3d.py
+++ b/comfy_extras/nodes_stable3d.py
@@ -46,7 +46,7 @@ class StableZero123_Conditioning:
encode_pixels = pixels[:,:,:,:3]
t = vae.encode(encode_pixels)
cam_embeds = camera_embeddings(elevation, azimuth)
- cond = torch.cat([pooled, cam_embeds.repeat((pooled.shape[0], 1, 1))], dim=-1)
+ cond = torch.cat([pooled, cam_embeds.to(pooled.device).repeat((pooled.shape[0], 1, 1))], dim=-1)
positive = [[cond, {"concat_latent_image": t}]]
negative = [[torch.zeros_like(pooled), {"concat_latent_image": torch.zeros_like(t)}]]