The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
convert Cosmos nodes to V3 schema (#9721)
Alexander Piskundcb883498337
diff --git a/comfy_extras/nodes_cosmos.py b/comfy_extras/nodes_cosmos.pyindex 4f4960551..7dd129d19 100644--- a/comfy_extras/nodes_cosmos.py+++ b/comfy_extras/nodes_cosmos.py@@ -1,25 +1,32 @@+from typing_extensions import overrideimport nodesimport torchimport comfy.model_managementimport comfy.utilsimport comfy.latent_formats+from comfy_api.latest import ComfyExtension, io-class EmptyCosmosLatentVideo:- @classmethod- def INPUT_TYPES(s):- return {"required": { "width": ("INT", {"default": 1280, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),- "height": ("INT", {"default": 704, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),- "length": ("INT", {"default": 121, "min": 1, "max": nodes.MAX_RESOLUTION, "step": 8}),- "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096})}}- RETURN_TYPES = ("LATENT",)- FUNCTION = "generate"- CATEGORY = "latent/video"+class EmptyCosmosLatentVideo(io.ComfyNode):+ @classmethod+ def define_schema(cls) -> io.Schema:+ return io.Schema(+ node_id="EmptyCosmosLatentVideo",+ category="latent/video",+ inputs=[+ io.Int.Input("width", default=1280, min=16, max=nodes.MAX_RESOLUTION, step=16),+ io.Int.Input("height", default=704, min=16, max=nodes.MAX_RESOLUTION, step=16),+ io.Int.Input("length", default=121, min=1, max=nodes.MAX_RESOLUTION, step=8),+ io.Int.Input("batch_size", default=1, min=1, max=4096),+ ],+ outputs=[io.Latent.Output()],+ )- def generate(self, width, height, length, batch_size=1):+ @classmethod+ def execute(cls, width, height, length, batch_size=1) -> io.NodeOutput:latent = torch.zeros([batch_size, 16, ((length - 1) // 8) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())- return ({"samples": latent}, )+ return io.NodeOutput({"samples": latent})def vae_encode_with_padding(vae, image, width, height, length, padding=0):@@ -33,31 +40,31 @@ def vae_encode_with_padding(vae, image, width, height, length, padding=0):return latent_temp[:, :, :latent_len]-class CosmosImageToVideoLatent:+class CosmosImageToVideoLatent(io.ComfyNode):@classmethod- def INPUT_TYPES(s):- return {"required": {"vae": ("VAE", ),- "width": ("INT", {"default": 1280, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),- "height": ("INT", {"default": 704, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),- "length": ("INT", {"default": 121, "min": 1, "max": nodes.MAX_RESOLUTION, "step": 8}),- "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),- },- "optional": {"start_image": ("IMAGE", ),- "end_image": ("IMAGE", ),- }}-+ def define_schema(cls) -> io.Schema:+ return io.Schema(+ node_id="CosmosImageToVideoLatent",+ category="conditioning/inpaint",+ inputs=[+ io.Vae.Input("vae"),+ io.Int.Input("width", default=1280, min=16, max=nodes.MAX_RESOLUTION, step=16),+ io.Int.Input("height", default=704, min=16, max=nodes.MAX_RESOLUTION, step=16),+ io.Int.Input("length", default=121, min=1, max=nodes.MAX_RESOLUTION, step=8),+ io.Int.Input("batch_size", default=1, min=1, max=4096),+ io.Image.Input("start_image", optional=True),+ io.Image.Input("end_image", optional=True),+ ],+ outputs=[io.Latent.Output()],+ )- RETURN_TYPES = ("LATENT",)- FUNCTION = "encode"-- CATEGORY = "conditioning/inpaint"-- def encode(self, vae, width, height, length, batch_size, start_image=None, end_image=None):+ @classmethod+ def execute(cls, vae, width, height, length, batch_size, start_image=None, end_image=None) -> io.NodeOutput:latent = torch.zeros([1, 16, ((length - 1) // 8) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())if start_image is None and end_image is None:out_latent = {}out_latent["samples"] = latent- return (out_latent,)+ return io.NodeOutput(out_latent)mask = torch.ones([latent.shape[0], 1, ((length - 1) // 8) + 1, latent.shape[-2], latent.shape[-1]], device=comfy.model_management.intermediate_device())@@ -74,33 +81,33 @@ class CosmosImageToVideoLatent:out_latent = {}out_latent["samples"] = latent.repeat((batch_size, ) + (1,) * (latent.ndim - 1))out_latent["noise_mask"] = mask.repeat((batch_size, ) + (1,) * (mask.ndim - 1))- return (out_latent,)+ return io.NodeOutput(out_latent)-class CosmosPredict2ImageToVideoLatent:+class CosmosPredict2ImageToVideoLatent(io.ComfyNode):@classmethod- def INPUT_TYPES(s):- return {"required": {"vae": ("VAE", ),- "width": ("INT", {"default": 848, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),- "height": ("INT", {"default": 480, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),- "length": ("INT", {"default": 93, "min": 1, "max": nodes.MAX_RESOLUTION, "step": 4}),- "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),- },- "optional": {"start_image": ("IMAGE", ),- "end_image": ("IMAGE", ),- }}+ def define_schema(cls) -> io.Schema:+ return io.Schema(+ node_id="CosmosPredict2ImageToVideoLatent",+ category="conditioning/inpaint",+ inputs=[+ io.Vae.Input("vae"),+ io.Int.Input("width", default=848, min=16, max=nodes.MAX_RESOLUTION, step=16),+ io.Int.Input("height", default=480, min=16, max=nodes.MAX_RESOLUTION, step=16),+ io.Int.Input("length", default=93, min=1, max=nodes.MAX_RESOLUTION, step=4),+ io.Int.Input("batch_size", default=1, min=1, max=4096),+ io.Image.Input("start_image", optional=True),+ io.Image.Input("end_image", optional=True),+ ],+ outputs=[io.Latent.Output()],+ )-- RETURN_TYPES = ("LATENT",)- FUNCTION = "encode"-- CATEGORY = "conditioning/inpaint"-- def encode(self, vae, width, height, length, batch_size, start_image=None, end_image=None):+ @classmethod+ def execute(cls, vae, width, height, length, batch_size, start_image=None, end_image=None) -> io.NodeOutput:latent = torch.zeros([1, 16, ((length - 1) // 4) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())if start_image is None and end_image is None:out_latent = {}out_latent["samples"] = latent- return (out_latent,)+ return io.NodeOutput(out_latent)mask = torch.ones([latent.shape[0], 1, ((length - 1) // 4) + 1, latent.shape[-2], latent.shape[-1]], device=comfy.model_management.intermediate_device())@@ -119,10 +126,18 @@ class CosmosPredict2ImageToVideoLatent:latent = latent_format.process_out(latent) * mask + latent * (1.0 - mask)out_latent["samples"] = latent.repeat((batch_size, ) + (1,) * (latent.ndim - 1))out_latent["noise_mask"] = mask.repeat((batch_size, ) + (1,) * (mask.ndim - 1))- return (out_latent,)+ return io.NodeOutput(out_latent)+++class CosmosExtension(ComfyExtension):+ @override+ async def get_node_list(self) -> list[type[io.ComfyNode]]:+ return [+ EmptyCosmosLatentVideo,+ CosmosImageToVideoLatent,+ CosmosPredict2ImageToVideoLatent,+ ]+-NODE_CLASS_MAPPINGS = {- "EmptyCosmosLatentVideo": EmptyCosmosLatentVideo,- "CosmosImageToVideoLatent": CosmosImageToVideoLatent,- "CosmosPredict2ImageToVideoLatent": CosmosPredict2ImageToVideoLatent,-}+async def comfy_entrypoint() -> CosmosExtension:+ return CosmosExtension()