254 lines
8.0 KiB
Python
Raw Normal View History

More API Nodes (#7956) * Add Ideogram generate node. * Add staging api. * Add API_NODE and common error for missing auth token (#5) * Add Minimax Video Generation + Async Task queue polling example (#6) * [Minimax] Show video preview and embed workflow in ouput (#7) * Remove uv.lock * Remove polling operations. * Revert "Remove polling operations." * Update stubs. * Added Ideogram and Minimax back in. * Added initial BFL Flux 1.1 [pro] Ultra node (#11) * Add --comfy-api-base launch arg (#13) * Add instructions for staging development. (#14) * remove validation to make it easier to run against LAN copies of the API * Manually add BFL polling status response schema (#15) * Add function for uploading files. (#18) * Add Luma nodes (#16) * Refactor util functions (#20) * Add VIDEO type (#21) * Add rest of Luma node functionality (#19) * Fix image_luma_ref not working (#28) * [Bug] Remove duplicated option T2V-01 in MinimaxTextToVideoNode (#31) * Add utils to map from pydantic model fields to comfy node inputs (#30) * add veo2, bump av req (#32) * Add Recraft nodes (#29) * Add Kling Nodes (#12) * Add Camera Concepts (luma_concepts) to Luma Video nodes (#33) * Add Runway nodes (#17) * Convert Minimax node to use VIDEO output type (#34) * Standard `CATEGORY` system for api nodes (#35) * Set `Content-Type` header when uploading files (#36) * add better error propagation to veo2 (#37) * Add Realistic Image and Logo Raster styles for Recraft v3 (#38) * Fix runway image upload and progress polling (#39) * Fix image upload for Luma: only include `Content-Type` header field if it's set explicitly (#40) * Moved Luma nodes to nodes_luma.py (#47) * Moved Recraft nodes to nodes_recraft.py (#48) * Add Pixverse nodes (#46) * Move and fix BFL nodes to node_bfl.py (#49) * Move and edit Minimax node to nodes_minimax.py (#50) * Add Minimax Image to Video node + Cleanup (#51) * Add Recraft Text to Vector node, add Save SVG node to handle its output (#53) * Added pixverse_template support to Pixverse Text to Video node (#54) * Added Recraft Controls + Recraft Color RGB nodes (#57) * split remaining nodes out of nodes_api, make utility lib, refactor ideogram (#61) * Add types and doctstrings to utils file (#64) * Fix: `PollingOperation` progress bar update progress by absolute value (#65) * Use common download function in kling nodes module (#67) * Fix: Luma video nodes in `api nodes/image` category (#68) * Set request type explicitly (#66) * Add `control_after_generate` to all seed inputs (#69) * Fix bug: deleting `Content-Type` when property does not exist (#73) * Add preview to Save SVG node (#74) * change default poll interval (#76), rework veo2 * Add Pixverse and updated Kling types (#75) * Added Pixverse Image to VIdeo node (#77) * Add Pixverse Transition Video node (#79) * Proper ray-1-6 support as fix has been applied in backend (#80) * Added Recraft Style - Infinite Style Library node (#82) * add ideogram v3 (#83) * [Kling] Split Camera Control config to its own node (#81) * Add Pika i2v and t2v nodes (#52) * Temporary Fix for Runway (#87) * Added Stability Stable Image Ultra node (#86) * Remove Runway nodes (#88) * Fix: Prompt text can't be validated in Kling nodes when using primitive nodes (#90) * Fix: typo in node name "Stabiliy" => "Stability" (#91) * Add String (Multiline) node (#93) * Update Pika Duration and Resolution options (#94) * Change base branch to master. Not main. (#95) * Fix UploadRequest file_name param (#98) * Removed Infinite Style Library until later (#99) * fix ideogram style types (#100) * fix multi image return (#101) * add metadata saving to SVG (#102) * Bump templates version to include API node template workflows (#104) * Fix: `download_url_to_video_output` return type (#103) * fix 4o generation bug (#106) * Serve SVG files directly (#107) * Add a bunch of nodes, 3 ready to use, the rest waiting for endpoint support (#108) * Revert "Serve SVG files directly" (#111) * Expose 4 remaining Recraft nodes (#112) * [Kling] Add `Duration` and `Video ID` outputs (#105) * Fix: datamodel-codegen sets string#binary type to non-existent `bytes_aliased` variable (#114) * Fix: Dall-e 2 not setting request content-type dynamically (#113) * Default request timeout: one hour. (#116) * Add Kling nodes: camera control, start-end frame, lip-sync, video extend (#115) * Add 8 nodes - 4 BFL, 4 Stability (#117) * Fix error for Recraft ImageToImage error for nonexistent random_seed param (#118) * Add remaining Pika nodes (#119) * Make controls input work for Recraft Image to Image node (#120) * Use upstream PR: Support saving Comfy VIDEO type to buffer (#123) * Use Upstream PR: "Fix: Error creating video when sliced audio tensor chunks are non-c-contiguous" (#127) * Improve audio upload utils (#128) * Fix: Nested `AnyUrl` in request model cannot be serialized (Kling, Runway) (#129) * Show errors and API output URLs to the user (change log levels) (#131) * Fix: Luma I2I fails when weight is <=0.01 (#132) * Change category of `LumaConcepts` node from image to video (#133) * Fix: `image.shape` accessed before `image` is null-checked (#134) * Apply small fixes and most prompt validation (if needed to avoid API error) (#135) * Node name/category modifications (#140) * Add back Recraft Style - Infinite Style Library node (#141) * Fixed Kling: Check attributes of pydantic types. (#144) * Bump `comfyui-workflow-templates` version (#142) * [Kling] Print response data when error validating response (#146) * Fix: error validating Kling image response, trying to use `"key" in` on Pydantic class instance (#147) * [Kling] Fix: Correct/verify supported subset of input combos in Kling nodes (#149) * [Kling] Fix typo in node description (#150) * [Kling] Fix: CFG min/max not being enforced (#151) * Rebase launch-rebase (private) on prep-branch (public copy of master) (#153) * Bump templates version (#154) * Fix: Kling image gen nodes don't return entire batch when `n` > 1 (#152) * Remove pixverse_template from PixVerse Transition Video node (#155) * Invert image_weight value on Luma Image to Image node (#156) * Invert and resize mask for Ideogram V3 node to match masking conventions (#158) * [Kling] Fix: image generation nodes not returning Tuple (#159) * [Bug] [Kling] Fix Kling camera control (#161) * Kling Image Gen v2 + improve node descriptions for Flux/OpenAI (#160) * [Kling] Don't return video_id from dual effect video (#162) * Bump frontend to 1.18.8 (#163) * Use 3.9 compat syntax (#164) * Use Python 3.10 * add example env var * Update templates to 0.1.11 * Bump frontend to 1.18.9 --------- Co-authored-by: Robin Huang <robin.j.huang@gmail.com> Co-authored-by: Christian Byrne <cbyrne@comfy.org> Co-authored-by: thot experiment <94414189+thot-experiment@users.noreply.github.com>
2025-05-06 03:23:00 -05:00
from __future__ import annotations
import torch
from enum import Enum
from typing import Optional, Union
from pydantic import BaseModel, Field, confloat
class LumaIO:
LUMA_REF = "LUMA_REF"
LUMA_CONCEPTS = "LUMA_CONCEPTS"
class LumaReference:
def __init__(self, image: torch.Tensor, weight: float):
self.image = image
self.weight = weight
def create_api_model(self, download_url: str):
return LumaImageRef(url=download_url, weight=self.weight)
class LumaReferenceChain:
def __init__(self, first_ref: LumaReference=None):
self.refs: list[LumaReference] = []
if first_ref:
self.refs.append(first_ref)
def add(self, luma_ref: LumaReference=None):
self.refs.append(luma_ref)
def create_api_model(self, download_urls: list[str], max_refs=4):
if len(self.refs) == 0:
return None
api_refs: list[LumaImageRef] = []
for ref, url in zip(self.refs, download_urls):
api_ref = LumaImageRef(url=url, weight=ref.weight)
api_refs.append(api_ref)
return api_refs
def clone(self):
c = LumaReferenceChain()
for ref in self.refs:
c.add(ref)
return c
class LumaConcept:
def __init__(self, key: str):
self.key = key
class LumaConceptChain:
def __init__(self, str_list: list[str] = None):
self.concepts: list[LumaConcept] = []
if str_list is not None:
for c in str_list:
if c != "None":
self.add(LumaConcept(key=c))
def add(self, concept: LumaConcept):
self.concepts.append(concept)
def create_api_model(self):
if len(self.concepts) == 0:
return None
api_concepts: list[LumaConceptObject] = []
for concept in self.concepts:
if concept.key == "None":
continue
api_concepts.append(LumaConceptObject(key=concept.key))
if len(api_concepts) == 0:
return None
return api_concepts
def clone(self):
c = LumaConceptChain()
for concept in self.concepts:
c.add(concept)
return c
def clone_and_merge(self, other: LumaConceptChain):
c = self.clone()
for concept in other.concepts:
c.add(concept)
return c
def get_luma_concepts(include_none=False):
concepts = []
if include_none:
concepts.append("None")
return concepts + [
"truck_left",
"pan_right",
"pedestal_down",
"low_angle",
"pedestal_up",
"selfie",
"pan_left",
"roll_right",
"zoom_in",
"over_the_shoulder",
"orbit_right",
"orbit_left",
"static",
"tiny_planet",
"high_angle",
"bolt_cam",
"dolly_zoom",
"overhead",
"zoom_out",
"handheld",
"roll_left",
"pov",
"aerial_drone",
"push_in",
"crane_down",
"truck_right",
"tilt_down",
"elevator_doors",
"tilt_up",
"ground_level",
"pull_out",
"aerial",
"crane_up",
"eye_level"
]
class LumaImageModel(str, Enum):
photon_1 = "photon-1"
photon_flash_1 = "photon-flash-1"
class LumaVideoModel(str, Enum):
ray_2 = "ray-2"
ray_flash_2 = "ray-flash-2"
ray_1_6 = "ray-1-6"
class LumaAspectRatio(str, Enum):
ratio_1_1 = "1:1"
ratio_16_9 = "16:9"
ratio_9_16 = "9:16"
ratio_4_3 = "4:3"
ratio_3_4 = "3:4"
ratio_21_9 = "21:9"
ratio_9_21 = "9:21"
class LumaVideoOutputResolution(str, Enum):
res_540p = "540p"
res_720p = "720p"
res_1080p = "1080p"
res_4k = "4k"
class LumaVideoModelOutputDuration(str, Enum):
dur_5s = "5s"
dur_9s = "9s"
class LumaGenerationType(str, Enum):
video = 'video'
image = 'image'
class LumaState(str, Enum):
queued = "queued"
dreaming = "dreaming"
completed = "completed"
failed = "failed"
class LumaAssets(BaseModel):
video: Optional[str] = Field(None, description='The URL of the video')
image: Optional[str] = Field(None, description='The URL of the image')
progress_video: Optional[str] = Field(None, description='The URL of the progress video')
class LumaImageRef(BaseModel):
'''Used for image gen'''
url: str = Field(..., description='The URL of the image reference')
weight: confloat(ge=0.0, le=1.0) = Field(..., description='The weight of the image reference')
class LumaImageReference(BaseModel):
'''Used for video gen'''
type: Optional[str] = Field('image', description='Input type, defaults to image')
url: str = Field(..., description='The URL of the image')
class LumaModifyImageRef(BaseModel):
url: str = Field(..., description='The URL of the image reference')
weight: confloat(ge=0.0, le=1.0) = Field(..., description='The weight of the image reference')
class LumaCharacterRef(BaseModel):
identity0: LumaImageIdentity = Field(..., description='The image identity object')
class LumaImageIdentity(BaseModel):
images: list[str] = Field(..., description='The URLs of the image identity')
class LumaGenerationReference(BaseModel):
type: str = Field('generation', description='Input type, defaults to generation')
id: str = Field(..., description='The ID of the generation')
class LumaKeyframes(BaseModel):
frame0: Optional[Union[LumaImageReference, LumaGenerationReference]] = Field(None, description='')
frame1: Optional[Union[LumaImageReference, LumaGenerationReference]] = Field(None, description='')
class LumaConceptObject(BaseModel):
key: str = Field(..., description='Camera Concept name')
class LumaImageGenerationRequest(BaseModel):
prompt: str = Field(..., description='The prompt of the generation')
model: LumaImageModel = Field(LumaImageModel.photon_1, description='The image model used for the generation')
aspect_ratio: Optional[LumaAspectRatio] = Field(LumaAspectRatio.ratio_16_9, description='The aspect ratio of the generation')
image_ref: Optional[list[LumaImageRef]] = Field(None, description='List of image reference objects')
style_ref: Optional[list[LumaImageRef]] = Field(None, description='List of style reference objects')
character_ref: Optional[LumaCharacterRef] = Field(None, description='The image identity object')
modify_image_ref: Optional[LumaModifyImageRef] = Field(None, description='The modify image reference object')
class LumaGenerationRequest(BaseModel):
prompt: str = Field(..., description='The prompt of the generation')
model: LumaVideoModel = Field(LumaVideoModel.ray_2, description='The video model used for the generation')
duration: Optional[LumaVideoModelOutputDuration] = Field(None, description='The duration of the generation')
aspect_ratio: Optional[LumaAspectRatio] = Field(None, description='The aspect ratio of the generation')
resolution: Optional[LumaVideoOutputResolution] = Field(None, description='The resolution of the generation')
loop: Optional[bool] = Field(None, description='Whether to loop the video')
keyframes: Optional[LumaKeyframes] = Field(None, description='The keyframes of the generation')
concepts: Optional[list[LumaConceptObject]] = Field(None, description='Camera Concepts to apply to generation')
class LumaGeneration(BaseModel):
id: str = Field(..., description='The ID of the generation')
generation_type: LumaGenerationType = Field(..., description='Generation type, image or video')
state: LumaState = Field(..., description='The state of the generation')
failure_reason: Optional[str] = Field(None, description='The reason for the state of the generation')
created_at: str = Field(..., description='The date and time when the generation was created')
assets: Optional[LumaAssets] = Field(None, description='The assets of the generation')
model: str = Field(..., description='The model used for the generation')
request: Union[LumaGenerationRequest, LumaImageGenerationRequest] = Field(..., description="The request used for the generation")