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.

Add InstructPixToPixConditioning node.

comfyanonymous1f8d8e6c772f
diff --git a/comfy_extras/nodes_ip2p.py b/comfy_extras/nodes_ip2p.py
new file mode 100644
index 000000000..c2e70a84c
--- /dev/null
+++ b/comfy_extras/nodes_ip2p.py
@@ -0,0 +1,45 @@
+import torch
+
+class InstructPixToPixConditioning:
+ @classmethod
+ def INPUT_TYPES(s):
+ return {"required": {"positive": ("CONDITIONING", ),
+ "negative": ("CONDITIONING", ),
+ "vae": ("VAE", ),
+ "pixels": ("IMAGE", ),
+ }}
+
+ RETURN_TYPES = ("CONDITIONING","CONDITIONING","LATENT")
+ RETURN_NAMES = ("positive", "negative", "latent")
+ FUNCTION = "encode"
+
+ CATEGORY = "conditioning/instructpix2pix"
+
+ def encode(self, positive, negative, pixels, vae):
+ x = (pixels.shape[1] // 8) * 8
+ y = (pixels.shape[2] // 8) * 8
+
+ if pixels.shape[1] != x or pixels.shape[2] != y:
+ x_offset = (pixels.shape[1] % 8) // 2
+ y_offset = (pixels.shape[2] % 8) // 2
+ pixels = pixels[:,x_offset:x + x_offset, y_offset:y + y_offset,:]
+
+ concat_latent = vae.encode(pixels)
+
+ out_latent = {}
+ out_latent["samples"] = torch.zeros_like(concat_latent)
+
+ out = []
+ for conditioning in [positive, negative]:
+ c = []
+ for t in conditioning:
+ d = t[1].copy()
+ d["concat_latent_image"] = concat_latent
+ n = [t[0], d]
+ c.append(n)
+ out.append(c)
+ return (out[0], out[1], out_latent)
+
+NODE_CLASS_MAPPINGS = {
+ "InstructPixToPixConditioning": InstructPixToPixConditioning,
+}
diff --git a/nodes.py b/nodes.py
index 5cf020df2..cdb82f801 100644
--- a/nodes.py
+++ b/nodes.py
@@ -1965,6 +1965,7 @@ def init_custom_nodes():
"nodes_morphology.py",
"nodes_stable_cascade.py",
"nodes_differential_diffusion.py",
+ "nodes_ip2p.py",
]
import_failed = []