mirrors/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-07-27 00:06:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update negative prompt for Moonvalley nodes (#9038)

Browse Source 
Co-authored-by: thorsten <thorsten@tripod-digital.co.nz>
This commit is contained in:
Thor-ATX 2025-07-26 09:27:03 +12:00 committed by GitHub
parent c0207b473f
commit c60467a148
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 224 additions and 135 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

359
comfy_api_nodes/nodes_moonvalley.py
View File

@ -2,7 +2,11 @@ import logging
from typing import Any, Callable, Optional, TypeVar
import random
import torch
from comfy_api_nodes.util.validation_utils import get_image_dimensions, validate_image_dimensions, validate_video_dimensions
from comfy_api_nodes.util.validation_utils import (
get_image_dimensions,
validate_image_dimensions,
validate_video_dimensions,
)
from comfy_api_nodes.apis import (
@ -10,7 +14,7 @@ from comfy_api_nodes.apis import (
MoonvalleyTextToVideoInferenceParams,
MoonvalleyVideoToVideoInferenceParams,
MoonvalleyVideoToVideoRequest,
MoonvalleyPromptResponse
MoonvalleyPromptResponse,
)
from comfy_api_nodes.apis.client import (
ApiEndpoint,
@ -54,20 +58,26 @@ MAX_VIDEO_SIZE = 1024 * 1024 * 1024 # 1 GB max for in-memory video processing
MOONVALLEY_MAREY_MAX_PROMPT_LENGTH = 5000
R = TypeVar("R")
class MoonvalleyApiError(Exception):
"""Base exception for Moonvalley API errors."""
pass
def is_valid_task_creation_response(response: MoonvalleyPromptResponse) -> bool:
"""Verifies that the initial response contains a task ID."""
return bool(response.id)
def validate_task_creation_response(response) -> None:
if not is_valid_task_creation_response(response):
error_msg = f"Moonvalley Marey API: Initial request failed. Code: {response.code}, Message: {response.message}, Data: {response}"
logging.error(error_msg)
raise MoonvalleyApiError(error_msg)
def get_video_from_response(response):
video = response.output_url
logging.info(
@ -102,16 +112,17 @@ def poll_until_finished(
poll_interval=16.0,
failed_statuses=["error"],
status_extractor=lambda response: (
response.status
if response and response.status
else None
response.status if response and response.status else None
),
auth_kwargs=auth_kwargs,
result_url_extractor=result_url_extractor,
node_id=node_id,
).execute()
def validate_prompts(prompt:str, negative_prompt: str, max_length=MOONVALLEY_MAREY_MAX_PROMPT_LENGTH):
def validate_prompts(
prompt: str, negative_prompt: str, max_length=MOONVALLEY_MAREY_MAX_PROMPT_LENGTH
):
"""Verifies that the prompt isn't empty and that neither prompt is too long."""
if not prompt:
raise ValueError("Positive prompt is empty")
@ -123,16 +134,15 @@ def validate_prompts(prompt:str, negative_prompt: str, max_length=MOONVALLEY_MAR
)
return True
def validate_input_media(width, height, with_frame_conditioning, num_frames_in=None):
# inference validation
# T = num_frames
# in all cases, the following must be true: T divisible by 16 and H,W by 8. in addition...
# with image conditioning: H*W must be divisible by 8192
# without image conditioning: T divisible by 32
if num_frames_in and not num_frames_in % 16 == 0 :
return False, (
"The input video total frame count must be divisible by 16!"
)
# inference validation
# T = num_frames
# in all cases, the following must be true: T divisible by 16 and H,W by 8. in addition...
# with image conditioning: H*W must be divisible by 8192
# without image conditioning: T divisible by 32
if num_frames_in and not num_frames_in % 16 == 0:
return False, ("The input video total frame count must be divisible by 16!")
if height % 8 != 0 or width % 8 != 0:
return False, (
@ -146,13 +156,13 @@ def validate_input_media(width, height, with_frame_conditioning, num_frames_in=N
"divisible by 8192 for frame conditioning"
)
else:
if num_frames_in and not num_frames_in % 32 == 0 :
return False, (
"The input video total frame count must be divisible by 32!"
)
if num_frames_in and not num_frames_in % 32 == 0:
return False, ("The input video total frame count must be divisible by 32!")
def validate_input_image(image: torch.Tensor, with_frame_conditioning: bool=False) -> None:
def validate_input_image(
image: torch.Tensor, with_frame_conditioning: bool = False
) -> None:
"""
Validates the input image adheres to the expectations of the API:
- The image resolution should not be less than 300*300px
@ -160,10 +170,15 @@ def validate_input_image(image: torch.Tensor, with_frame_conditioning: bool=Fals
"""
height, width = get_image_dimensions(image)
validate_input_media(width, height, with_frame_conditioning )
validate_image_dimensions(image, min_width=300, min_height=300, max_height=MAX_HEIGHT, max_width=MAX_WIDTH)
validate_input_media(width, height, with_frame_conditioning)
validate_image_dimensions(
image, min_width=300, min_height=300, max_height=MAX_HEIGHT, max_width=MAX_WIDTH
)
def validate_input_video(video: VideoInput, num_frames_out: int, with_frame_conditioning: bool=False):
def validate_input_video(
video: VideoInput, num_frames_out: int, with_frame_conditioning: bool = False
):
try:
width, height = video.get_dimensions()
except Exception as e:
@ -171,7 +186,13 @@ def validate_input_video(video: VideoInput, num_frames_out: int, with_frame_cond
raise ValueError(f"Cannot get video dimensions: {e}") from e
validate_input_media(width, height, with_frame_conditioning)
validate_video_dimensions(video, min_width=MIN_VID_WIDTH, min_height=MIN_VID_HEIGHT, max_width=MAX_VID_WIDTH, max_height=MAX_VID_HEIGHT)
validate_video_dimensions(
video,
min_width=MIN_VID_WIDTH,
min_height=MIN_VID_HEIGHT,
max_width=MAX_VID_WIDTH,
max_height=MAX_VID_HEIGHT,
)
trimmed_video = validate_input_video_length(video, num_frames_out)
return trimmed_video
@ -180,22 +201,29 @@ def validate_input_video(video: VideoInput, num_frames_out: int, with_frame_cond
def validate_input_video_length(video: VideoInput, num_frames: int):
if video.get_duration() > 60:
raise MoonvalleyApiError("Input Video lenth should be less than 1min. Please trim.")
raise MoonvalleyApiError(
"Input Video lenth should be less than 1min. Please trim."
)
if num_frames == 128:
if video.get_duration() < 5:
raise MoonvalleyApiError("Input Video length is less than 5s. Please use a video longer than or equal to 5s.")
if video.get_duration() > 5:
# trim video to 5s
video = trim_video(video, 5)
if video.get_duration() < 5:
raise MoonvalleyApiError(
"Input Video length is less than 5s. Please use a video longer than or equal to 5s."
)
if video.get_duration() > 5:
# trim video to 5s
video = trim_video(video, 5)
if num_frames == 256:
if video.get_duration() < 10:
raise MoonvalleyApiError("Input Video length is less than 10s. Please use a video longer than or equal to 10s.")
raise MoonvalleyApiError(
"Input Video length is less than 10s. Please use a video longer than or equal to 10s."
)
if video.get_duration() > 10:
# trim video to 10s
video = trim_video(video, 10)
return video
def trim_video(video: VideoInput, duration_sec: float) -> VideoInput:
"""
Returns a new VideoInput object trimmed from the beginning to the specified duration,
@ -219,8 +247,8 @@ def trim_video(video: VideoInput, duration_sec: float) -> VideoInput:
input_source = video.get_stream_source()
# Open containers
input_container = av.open(input_source, mode='r')
output_container = av.open(output_buffer, mode='w', format='mp4')
input_container = av.open(input_source, mode="r")
output_container = av.open(output_buffer, mode="w", format="mp4")
# Set up output streams for re-encoding
video_stream = None
@ -230,22 +258,32 @@ def trim_video(video: VideoInput, duration_sec: float) -> VideoInput:
logging.info(f"Found stream: type={stream.type}, class={type(stream)}")
if isinstance(stream, av.VideoStream):
# Create output video stream with same parameters
video_stream = output_container.add_stream('h264', rate=stream.average_rate)
video_stream = output_container.add_stream(
"h264", rate=stream.average_rate
)
video_stream.width = stream.width
video_stream.height = stream.height
video_stream.pix_fmt = 'yuv420p'
logging.info(f"Added video stream: {stream.width}x{stream.height} @ {stream.average_rate}fps")
video_stream.pix_fmt = "yuv420p"
logging.info(
f"Added video stream: {stream.width}x{stream.height} @ {stream.average_rate}fps"
)
elif isinstance(stream, av.AudioStream):
# Create output audio stream with same parameters
audio_stream = output_container.add_stream('aac', rate=stream.sample_rate)
audio_stream = output_container.add_stream(
"aac", rate=stream.sample_rate
)
audio_stream.sample_rate = stream.sample_rate
audio_stream.layout = stream.layout
logging.info(f"Added audio stream: {stream.sample_rate}Hz, {stream.channels} channels")
logging.info(
f"Added audio stream: {stream.sample_rate}Hz, {stream.channels} channels"
)
# Calculate target frame count that's divisible by 32
fps = input_container.streams.video[0].average_rate
estimated_frames = int(duration_sec * fps)
target_frames = (estimated_frames // 32) * 32 # Round down to nearest multiple of 32
target_frames = (
estimated_frames // 32
) * 32 # Round down to nearest multiple of 32
if target_frames == 0:
raise ValueError("Video too short: need at least 32 frames for Moonvalley")
@ -268,7 +306,9 @@ def trim_video(video: VideoInput, duration_sec: float) -> VideoInput:
for packet in video_stream.encode():
output_container.mux(packet)
logging.info(f"Encoded {frame_count} video frames (target: {target_frames})")
logging.info(
f"Encoded {frame_count} video frames (target: {target_frames})"
)
# Decode and re-encode audio frames
if audio_stream:
@ -292,7 +332,6 @@ def trim_video(video: VideoInput, duration_sec: float) -> VideoInput:
output_container.close()
input_container.close()
# Return as VideoFromFile using the buffer
output_buffer.seek(0)
return VideoFromFile(output_buffer)
@ -305,6 +344,7 @@ def trim_video(video: VideoInput, duration_sec: float) -> VideoInput:
output_container.close()
raise RuntimeError(f"Failed to trim video: {str(e)}") from e
# --- BaseMoonvalleyVideoNode ---
class BaseMoonvalleyVideoNode:
def parseWidthHeightFromRes(self, resolution: str):
@ -328,7 +368,7 @@ class BaseMoonvalleyVideoNode:
"Motion Transfer": "motion_control",
"Canny": "canny_control",
"Pose Transfer": "pose_control",
"Depth": "depth_control"
"Depth": "depth_control",
}
if value in control_map:
return control_map[value]
@ -355,31 +395,63 @@ class BaseMoonvalleyVideoNode:
return {
"required": {
"prompt": model_field_to_node_input(
IO.STRING, MoonvalleyTextToVideoRequest, "prompt_text",
multiline=True
IO.STRING,
MoonvalleyTextToVideoRequest,
"prompt_text",
multiline=True,
),
"negative_prompt": model_field_to_node_input(
IO.STRING,
MoonvalleyTextToVideoInferenceParams,
"negative_prompt",
multiline=True,
default="gopro, bright, contrast, static, overexposed, bright, vignette, artifacts, still, noise, texture, scanlines, videogame, 360 camera, VR, transition, flare, saturation, distorted, warped, wide angle, contrast, saturated, vibrant, glowing, cross dissolve, texture, videogame, saturation, cheesy, ugly hands, mutated hands, mutant, disfigured, extra fingers, blown out, horrible, blurry, worst quality, bad, transition, dissolve, cross-dissolve, melt, fade in, fade out, wobbly, weird, low quality, plastic, stock footage, video camera, boring, static",
default="low-poly, flat shader, bad rigging, stiff animation, uncanny eyes, low-quality textures, looping glitch, cheap effect, overbloom, bloom spam, default lighting, game asset, stiff face, ugly specular, AI artifacts",
),
"resolution": (IO.COMBO, {
"options": ["16:9 (1920 x 1080)",
"9:16 (1080 x 1920)",
"1:1 (1152 x 1152)",
"4:3 (1440 x 1080)",
"3:4 (1080 x 1440)",
"21:9 (2560 x 1080)"],
"resolution": (
IO.COMBO,
{
"options": [
"16:9 (1920 x 1080)",
"9:16 (1080 x 1920)",
"1:1 (1152 x 1152)",
"4:3 (1440 x 1080)",
"3:4 (1080 x 1440)",
"21:9 (2560 x 1080)",
],
"default": "16:9 (1920 x 1080)",
"tooltip": "Resolution of the output video",
}),
},
),
# "length": (IO.COMBO,{"options":['5s','10s'], "default": '5s'}),
"prompt_adherence": model_field_to_node_input(IO.FLOAT,MoonvalleyTextToVideoInferenceParams,"guidance_scale",default=7.0, step=1, min=1, max=20),
"seed": model_field_to_node_input(IO.INT,MoonvalleyTextToVideoInferenceParams, "seed", default=random.randint(0, 2**32 - 1), min=0, max=4294967295, step=1, display="number", tooltip="Random seed value", control_after_generate=True),
"steps": model_field_to_node_input(IO.INT, MoonvalleyTextToVideoInferenceParams, "steps", default=100, min=1, max=100),
"prompt_adherence": model_field_to_node_input(
IO.FLOAT,
MoonvalleyTextToVideoInferenceParams,
"guidance_scale",
default=7.0,
step=1,
min=1,
max=20,
),
"seed": model_field_to_node_input(
IO.INT,
MoonvalleyTextToVideoInferenceParams,
"seed",
default=random.randint(0, 2**32 - 1),
min=0,
max=4294967295,
step=1,
display="number",
tooltip="Random seed value",
control_after_generate=True,
),
"steps": model_field_to_node_input(
IO.INT,
MoonvalleyTextToVideoInferenceParams,
"steps",
default=100,
min=1,
max=100,
),
},
"hidden": {
"auth_token": "AUTH_TOKEN_COMFY_ORG",
@ -393,7 +465,7 @@ class BaseMoonvalleyVideoNode:
"image_url",
tooltip="The reference image used to generate the video",
),
}
},
}
RETURN_TYPES = ("STRING",)
@ -404,6 +476,7 @@ class BaseMoonvalleyVideoNode:
def generate(self, **kwargs):
return None
# --- MoonvalleyImg2VideoNode ---
class MoonvalleyImg2VideoNode(BaseMoonvalleyVideoNode):
@ -415,43 +488,46 @@ class MoonvalleyImg2VideoNode(BaseMoonvalleyVideoNode):
RETURN_NAMES = ("video",)
DESCRIPTION = "Moonvalley Marey Image to Video Node"
def generate(self, prompt, negative_prompt, unique_id: Optional[str] = None, **kwargs):
def generate(
self, prompt, negative_prompt, unique_id: Optional[str] = None, **kwargs
):
image = kwargs.get("image", None)
if (image is None):
if image is None:
raise MoonvalleyApiError("image is required")
total_frames = get_total_frames_from_length()
validate_input_image(image,True)
validate_input_image(image, True)
validate_prompts(prompt, negative_prompt, MOONVALLEY_MAREY_MAX_PROMPT_LENGTH)
width_height = self.parseWidthHeightFromRes(kwargs.get("resolution"))
inference_params=MoonvalleyTextToVideoInferenceParams(
negative_prompt=negative_prompt,
steps=kwargs.get("steps"),
seed=kwargs.get("seed"),
guidance_scale=kwargs.get("prompt_adherence"),
num_frames=total_frames,
width=width_height.get("width"),
height=width_height.get("height"),
use_negative_prompts=True
)
inference_params = MoonvalleyTextToVideoInferenceParams(
negative_prompt=negative_prompt,
steps=kwargs.get("steps"),
seed=kwargs.get("seed"),
guidance_scale=kwargs.get("prompt_adherence"),
num_frames=total_frames,
width=width_height.get("width"),
height=width_height.get("height"),
use_negative_prompts=True,
)
"""Upload image to comfy backend to have a URL available for further processing"""
# Get MIME type from tensor - assuming PNG format for image tensors
mime_type = "image/png"
image_url = upload_images_to_comfyapi(image, max_images=1, auth_kwargs=kwargs, mime_type=mime_type)[0]
image_url = upload_images_to_comfyapi(
image, max_images=1, auth_kwargs=kwargs, mime_type=mime_type
)[0]
request = MoonvalleyTextToVideoRequest(
image_url=image_url,
prompt_text=prompt,
inference_params=inference_params
)
image_url=image_url, prompt_text=prompt, inference_params=inference_params
)
initial_operation = SynchronousOperation(
endpoint=ApiEndpoint(path=API_IMG2VIDEO_ENDPOINT,
method=HttpMethod.POST,
request_model=MoonvalleyTextToVideoRequest,
response_model=MoonvalleyPromptResponse
),
endpoint=ApiEndpoint(
path=API_IMG2VIDEO_ENDPOINT,
method=HttpMethod.POST,
request_model=MoonvalleyTextToVideoRequest,
response_model=MoonvalleyPromptResponse,
),
request=request,
auth_kwargs=kwargs,
)
@ -463,7 +539,8 @@ class MoonvalleyImg2VideoNode(BaseMoonvalleyVideoNode):
task_id, auth_kwargs=kwargs, node_id=unique_id
)
video = download_url_to_video_output(final_response.output_url)
return (video, )
return (video,)
# --- MoonvalleyVid2VidNode ---
class MoonvalleyVideo2VideoNode(BaseMoonvalleyVideoNode):
@ -479,38 +556,46 @@ class MoonvalleyVideo2VideoNode(BaseMoonvalleyVideoNode):
if param in input_types["optional"]:
del input_types["optional"][param]
input_types["optional"] = {
"video": (IO.VIDEO, {"default": "", "multiline": False, "tooltip": "The reference video used to generate the output video. Input a 5s video for 128 frames and a 10s video for 256 frames. Longer videos will be trimmed automatically."}),
"control_type": (
["Motion Transfer", "Pose Transfer"],
{"default": "Motion Transfer"},
),
"motion_intensity": (
"INT",
{
"default": 100,
"step": 1,
"min": 0,
"max": 100,
"tooltip": "Only used if control_type is 'Motion Transfer'",
},
)
}
"video": (
IO.VIDEO,
{
"default": "",
"multiline": False,
"tooltip": "The reference video used to generate the output video. Input a 5s video for 128 frames and a 10s video for 256 frames. Longer videos will be trimmed automatically.",
},
),
"control_type": (
["Motion Transfer", "Pose Transfer"],
{"default": "Motion Transfer"},
),
"motion_intensity": (
"INT",
{
"default": 100,
"step": 1,
"min": 0,
"max": 100,
"tooltip": "Only used if control_type is 'Motion Transfer'",
},
),
}
return input_types
RETURN_TYPES = ("VIDEO",)
RETURN_NAMES = ("video",)
def generate(self, prompt, negative_prompt, unique_id: Optional[str] = None, **kwargs):
def generate(
self, prompt, negative_prompt, unique_id: Optional[str] = None, **kwargs
):
video = kwargs.get("video")
num_frames = get_total_frames_from_length()
if not video :
if not video:
raise MoonvalleyApiError("video is required")
"""Validate video input"""
video_url=""
video_url = ""
if video:
validated_video = validate_input_video(video, num_frames, False)
video_url = upload_video_to_comfyapi(validated_video, auth_kwargs=kwargs)
@ -520,29 +605,30 @@ class MoonvalleyVideo2VideoNode(BaseMoonvalleyVideoNode):
"""Validate prompts and inference input"""
validate_prompts(prompt, negative_prompt)
inference_params=MoonvalleyVideoToVideoInferenceParams(
inference_params = MoonvalleyVideoToVideoInferenceParams(
negative_prompt=negative_prompt,
steps=kwargs.get("steps"),
seed=kwargs.get("seed"),
guidance_scale=kwargs.get("prompt_adherence"),
control_params={'motion_intensity': motion_intensity}
control_params={"motion_intensity": motion_intensity},
)
control = self.parseControlParameter(control_type)
request = MoonvalleyVideoToVideoRequest(
control_type=control,
video_url=video_url,
prompt_text=prompt,
inference_params=inference_params
)
control_type=control,
video_url=video_url,
prompt_text=prompt,
inference_params=inference_params,
)
initial_operation = SynchronousOperation(
endpoint=ApiEndpoint(path=API_VIDEO2VIDEO_ENDPOINT,
method=HttpMethod.POST,
request_model=MoonvalleyVideoToVideoRequest,
response_model=MoonvalleyPromptResponse
),
endpoint=ApiEndpoint(
path=API_VIDEO2VIDEO_ENDPOINT,
method=HttpMethod.POST,
request_model=MoonvalleyVideoToVideoRequest,
response_model=MoonvalleyPromptResponse,
),
request=request,
auth_kwargs=kwargs,
)
@ -556,7 +642,8 @@ class MoonvalleyVideo2VideoNode(BaseMoonvalleyVideoNode):
video = download_url_to_video_output(final_response.output_url)
return (video, )
return (video,)
# --- MoonvalleyTxt2VideoNode ---
class MoonvalleyTxt2VideoNode(BaseMoonvalleyVideoNode):
@ -575,31 +662,33 @@ class MoonvalleyTxt2VideoNode(BaseMoonvalleyVideoNode):
del input_types["optional"][param]
return input_types
def generate(self, prompt, negative_prompt, unique_id: Optional[str] = None, **kwargs):
def generate(
self, prompt, negative_prompt, unique_id: Optional[str] = None, **kwargs
):
validate_prompts(prompt, negative_prompt, MOONVALLEY_MAREY_MAX_PROMPT_LENGTH)
width_height = self.parseWidthHeightFromRes(kwargs.get("resolution"))
num_frames = get_total_frames_from_length()
inference_params=MoonvalleyTextToVideoInferenceParams(
negative_prompt=negative_prompt,
steps=kwargs.get("steps"),
seed=kwargs.get("seed"),
guidance_scale=kwargs.get("prompt_adherence"),
num_frames=num_frames,
width=width_height.get("width"),
height=width_height.get("height"),
)
inference_params = MoonvalleyTextToVideoInferenceParams(
negative_prompt=negative_prompt,
steps=kwargs.get("steps"),
seed=kwargs.get("seed"),
guidance_scale=kwargs.get("prompt_adherence"),
num_frames=num_frames,
width=width_height.get("width"),
height=width_height.get("height"),
)
request = MoonvalleyTextToVideoRequest(
prompt_text=prompt,
inference_params=inference_params
)
prompt_text=prompt, inference_params=inference_params
)
initial_operation = SynchronousOperation(
endpoint=ApiEndpoint(path=API_TXT2VIDEO_ENDPOINT,
method=HttpMethod.POST,
request_model=MoonvalleyTextToVideoRequest,
response_model=MoonvalleyPromptResponse
),
endpoint=ApiEndpoint(
path=API_TXT2VIDEO_ENDPOINT,
method=HttpMethod.POST,
request_model=MoonvalleyTextToVideoRequest,
response_model=MoonvalleyPromptResponse,
),
request=request,
auth_kwargs=kwargs,
)
@ -612,8 +701,7 @@ class MoonvalleyTxt2VideoNode(BaseMoonvalleyVideoNode):
)
video = download_url_to_video_output(final_response.output_url)
return (video, )
return (video,)
NODE_CLASS_MAPPINGS = {
@ -629,6 +717,7 @@ NODE_DISPLAY_NAME_MAPPINGS = {
# "MoonvalleyVideo2VideoNode": "Moonvalley Marey Video to Video",
}
def get_total_frames_from_length(length="5s"):
# if length == '5s':
# return 128