xinyun/ComfyUI
1
0
Fork 0
mirror of https://git.datalinker.icu/comfyanonymous/ComfyUI synced 2025-12-11 06:54:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

convert nodes_stable3d.py to V3 schema (#10204)

Browse Source
This commit is contained in:
Alexander Piskun 2025-10-04 22:33:48 +03:00 committed by GitHub
parent 2ed74f7ac7
commit b1fa1922df
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 86 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

149
comfy_extras/nodes_stable3d.py
View File

@ -1,6 +1,8 @@
import torch import torch
import nodes import nodes
import comfy.utils import comfy.utils
from typing_extensions import override
from comfy_api.latest import ComfyExtension, io
def camera_embeddings(elevation, azimuth): def camera_embeddings(elevation, azimuth):
elevation = torch.as_tensor([elevation]) elevation = torch.as_tensor([elevation])
@ -20,26 +22,31 @@ def camera_embeddings(elevation, azimuth):
return embeddings return embeddings
class StableZero123_Conditioning: class StableZero123_Conditioning(io.ComfyNode):
@classmethod @classmethod
def INPUT_TYPES(s): def define_schema(cls):
return {"required": { "clip_vision": ("CLIP_VISION",), return io.Schema(
"init_image": ("IMAGE",), node_id="StableZero123_Conditioning",
"vae": ("VAE",), category="conditioning/3d_models",
"width": ("INT", {"default": 256, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 8}), inputs=[
"height": ("INT", {"default": 256, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 8}), io.ClipVision.Input("clip_vision"),
"batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}), io.Image.Input("init_image"),
"elevation": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0, "step": 0.1, "round": False}), io.Vae.Input("vae"),
"azimuth": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0, "step": 0.1, "round": False}), io.Int.Input("width", default=256, min=16, max=nodes.MAX_RESOLUTION, step=8),
}} io.Int.Input("height", default=256, min=16, max=nodes.MAX_RESOLUTION, step=8),
RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT") io.Int.Input("batch_size", default=1, min=1, max=4096),
RETURN_NAMES = ("positive", "negative", "latent") io.Float.Input("elevation", default=0.0, min=-180.0, max=180.0, step=0.1, round=False),
io.Float.Input("azimuth", default=0.0, min=-180.0, max=180.0, step=0.1, round=False)
],
outputs=[
io.Conditioning.Output(display_name="positive"),
io.Conditioning.Output(display_name="negative"),
io.Latent.Output(display_name="latent")
]
)
FUNCTION = "encode" @classmethod
def execute(cls, clip_vision, init_image, vae, width, height, batch_size, elevation, azimuth) -> io.NodeOutput:
CATEGORY = "conditioning/3d_models"
def encode(self, clip_vision, init_image, vae, width, height, batch_size, elevation, azimuth):
output = clip_vision.encode_image(init_image) output = clip_vision.encode_image(init_image)
pooled = output.image_embeds.unsqueeze(0) pooled = output.image_embeds.unsqueeze(0)
pixels = comfy.utils.common_upscale(init_image.movedim(-1,1), width, height, "bilinear", "center").movedim(1,-1) pixels = comfy.utils.common_upscale(init_image.movedim(-1,1), width, height, "bilinear", "center").movedim(1,-1)
@ -51,30 +58,35 @@ class StableZero123_Conditioning:
positive = [[cond, {"concat_latent_image": t}]] positive = [[cond, {"concat_latent_image": t}]]
negative = [[torch.zeros_like(pooled), {"concat_latent_image": torch.zeros_like(t)}]] negative = [[torch.zeros_like(pooled), {"concat_latent_image": torch.zeros_like(t)}]]
latent = torch.zeros([batch_size, 4, height // 8, width // 8]) latent = torch.zeros([batch_size, 4, height // 8, width // 8])
return (positive, negative, {"samples":latent}) return io.NodeOutput(positive, negative, {"samples":latent})
class StableZero123_Conditioning_Batched: class StableZero123_Conditioning_Batched(io.ComfyNode):
@classmethod @classmethod
def INPUT_TYPES(s): def define_schema(cls):
return {"required": { "clip_vision": ("CLIP_VISION",), return io.Schema(
"init_image": ("IMAGE",), node_id="StableZero123_Conditioning_Batched",
"vae": ("VAE",), category="conditioning/3d_models",
"width": ("INT", {"default": 256, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 8}), inputs=[
"height": ("INT", {"default": 256, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 8}), io.ClipVision.Input("clip_vision"),
"batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}), io.Image.Input("init_image"),
"elevation": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0, "step": 0.1, "round": False}), io.Vae.Input("vae"),
"azimuth": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0, "step": 0.1, "round": False}), io.Int.Input("width", default=256, min=16, max=nodes.MAX_RESOLUTION, step=8),
"elevation_batch_increment": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0, "step": 0.1, "round": False}), io.Int.Input("height", default=256, min=16, max=nodes.MAX_RESOLUTION, step=8),
"azimuth_batch_increment": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0, "step": 0.1, "round": False}), io.Int.Input("batch_size", default=1, min=1, max=4096),
}} io.Float.Input("elevation", default=0.0, min=-180.0, max=180.0, step=0.1, round=False),
RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT") io.Float.Input("azimuth", default=0.0, min=-180.0, max=180.0, step=0.1, round=False),
RETURN_NAMES = ("positive", "negative", "latent") io.Float.Input("elevation_batch_increment", default=0.0, min=-180.0, max=180.0, step=0.1, round=False),
io.Float.Input("azimuth_batch_increment", default=0.0, min=-180.0, max=180.0, step=0.1, round=False)
],
outputs=[
io.Conditioning.Output(display_name="positive"),
io.Conditioning.Output(display_name="negative"),
io.Latent.Output(display_name="latent")
]
)
FUNCTION = "encode" @classmethod
def execute(cls, clip_vision, init_image, vae, width, height, batch_size, elevation, azimuth, elevation_batch_increment, azimuth_batch_increment) -> io.NodeOutput:
CATEGORY = "conditioning/3d_models"
def encode(self, clip_vision, init_image, vae, width, height, batch_size, elevation, azimuth, elevation_batch_increment, azimuth_batch_increment):
output = clip_vision.encode_image(init_image) output = clip_vision.encode_image(init_image)
pooled = output.image_embeds.unsqueeze(0) pooled = output.image_embeds.unsqueeze(0)
pixels = comfy.utils.common_upscale(init_image.movedim(-1,1), width, height, "bilinear", "center").movedim(1,-1) pixels = comfy.utils.common_upscale(init_image.movedim(-1,1), width, height, "bilinear", "center").movedim(1,-1)
@ -93,27 +105,32 @@ class StableZero123_Conditioning_Batched:
positive = [[cond, {"concat_latent_image": t}]] positive = [[cond, {"concat_latent_image": t}]]
negative = [[torch.zeros_like(pooled), {"concat_latent_image": torch.zeros_like(t)}]] negative = [[torch.zeros_like(pooled), {"concat_latent_image": torch.zeros_like(t)}]]
latent = torch.zeros([batch_size, 4, height // 8, width // 8]) latent = torch.zeros([batch_size, 4, height // 8, width // 8])
return (positive, negative, {"samples":latent, "batch_index": [0] * batch_size}) return io.NodeOutput(positive, negative, {"samples":latent, "batch_index": [0] * batch_size})
class SV3D_Conditioning: class SV3D_Conditioning(io.ComfyNode):
@classmethod @classmethod
def INPUT_TYPES(s): def define_schema(cls):
return {"required": { "clip_vision": ("CLIP_VISION",), return io.Schema(
"init_image": ("IMAGE",), node_id="SV3D_Conditioning",
"vae": ("VAE",), category="conditioning/3d_models",
"width": ("INT", {"default": 576, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 8}), inputs=[
"height": ("INT", {"default": 576, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 8}), io.ClipVision.Input("clip_vision"),
"video_frames": ("INT", {"default": 21, "min": 1, "max": 4096}), io.Image.Input("init_image"),
"elevation": ("FLOAT", {"default": 0.0, "min": -90.0, "max": 90.0, "step": 0.1, "round": False}), io.Vae.Input("vae"),
}} io.Int.Input("width", default=576, min=16, max=nodes.MAX_RESOLUTION, step=8),
RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT") io.Int.Input("height", default=576, min=16, max=nodes.MAX_RESOLUTION, step=8),
RETURN_NAMES = ("positive", "negative", "latent") io.Int.Input("video_frames", default=21, min=1, max=4096),
io.Float.Input("elevation", default=0.0, min=-90.0, max=90.0, step=0.1, round=False)
],
outputs=[
io.Conditioning.Output(display_name="positive"),
io.Conditioning.Output(display_name="negative"),
io.Latent.Output(display_name="latent")
]
)
FUNCTION = "encode" @classmethod
def execute(cls, clip_vision, init_image, vae, width, height, video_frames, elevation) -> io.NodeOutput:
CATEGORY = "conditioning/3d_models"
def encode(self, clip_vision, init_image, vae, width, height, video_frames, elevation):
output = clip_vision.encode_image(init_image) output = clip_vision.encode_image(init_image)
pooled = output.image_embeds.unsqueeze(0) pooled = output.image_embeds.unsqueeze(0)
pixels = comfy.utils.common_upscale(init_image.movedim(-1,1), width, height, "bilinear", "center").movedim(1,-1) pixels = comfy.utils.common_upscale(init_image.movedim(-1,1), width, height, "bilinear", "center").movedim(1,-1)
@ -133,11 +150,17 @@ class SV3D_Conditioning:
positive = [[pooled, {"concat_latent_image": t, "elevation": elevations, "azimuth": azimuths}]] positive = [[pooled, {"concat_latent_image": t, "elevation": elevations, "azimuth": azimuths}]]
negative = [[torch.zeros_like(pooled), {"concat_latent_image": torch.zeros_like(t), "elevation": elevations, "azimuth": azimuths}]] negative = [[torch.zeros_like(pooled), {"concat_latent_image": torch.zeros_like(t), "elevation": elevations, "azimuth": azimuths}]]
latent = torch.zeros([video_frames, 4, height // 8, width // 8]) latent = torch.zeros([video_frames, 4, height // 8, width // 8])
return (positive, negative, {"samples":latent}) return io.NodeOutput(positive, negative, {"samples":latent})
NODE_CLASS_MAPPINGS = { class Stable3DExtension(ComfyExtension):
"StableZero123_Conditioning": StableZero123_Conditioning, @override
"StableZero123_Conditioning_Batched": StableZero123_Conditioning_Batched, async def get_node_list(self) -> list[type[io.ComfyNode]]:
"SV3D_Conditioning": SV3D_Conditioning, return [
} StableZero123_Conditioning,
StableZero123_Conditioning_Batched,
SV3D_Conditioning,
]
async def comfy_entrypoint() -> Stable3DExtension:
return Stable3DExtension()