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.pynew file mode 100644index 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.pyindex 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 = []