mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2025-06-07 20:12:57 +08:00

* 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>
264 lines
8.7 KiB
Python
264 lines
8.7 KiB
Python
from __future__ import annotations
|
|
|
|
|
|
|
|
from enum import Enum
|
|
from typing import Optional
|
|
|
|
from pydantic import BaseModel, Field, conint, confloat
|
|
|
|
|
|
class RecraftColor:
|
|
def __init__(self, r: int, g: int, b: int):
|
|
self.color = [r, g, b]
|
|
|
|
def create_api_model(self):
|
|
return RecraftColorObject(rgb=self.color)
|
|
|
|
|
|
class RecraftColorChain:
|
|
def __init__(self):
|
|
self.colors: list[RecraftColor] = []
|
|
|
|
def get_first(self):
|
|
if len(self.colors) > 0:
|
|
return self.colors[0]
|
|
return None
|
|
|
|
def add(self, color: RecraftColor):
|
|
self.colors.append(color)
|
|
|
|
def create_api_model(self):
|
|
if not self.colors:
|
|
return None
|
|
colors_api = [x.create_api_model() for x in self.colors]
|
|
return colors_api
|
|
|
|
def clone(self):
|
|
c = RecraftColorChain()
|
|
for color in self.colors:
|
|
c.add(color)
|
|
return c
|
|
|
|
def clone_and_merge(self, other: RecraftColorChain):
|
|
c = self.clone()
|
|
for color in other.colors:
|
|
c.add(color)
|
|
return c
|
|
|
|
|
|
class RecraftControls:
|
|
def __init__(self, colors: RecraftColorChain=None, background_color: RecraftColorChain=None,
|
|
artistic_level: int=None, no_text: bool=None):
|
|
self.colors = colors
|
|
self.background_color = background_color
|
|
self.artistic_level = artistic_level
|
|
self.no_text = no_text
|
|
|
|
def create_api_model(self):
|
|
if self.colors is None and self.background_color is None and self.artistic_level is None and self.no_text is None:
|
|
return None
|
|
colors_api = None
|
|
background_color_api = None
|
|
if self.colors:
|
|
colors_api = self.colors.create_api_model()
|
|
if self.background_color:
|
|
first_background = self.background_color.get_first()
|
|
background_color_api = first_background.create_api_model() if first_background else None
|
|
|
|
return RecraftControlsObject(colors=colors_api, background_color=background_color_api,
|
|
artistic_level=self.artistic_level, no_text=self.no_text)
|
|
|
|
|
|
class RecraftStyle:
|
|
def __init__(self, style: str=None, substyle: str=None, style_id: str=None):
|
|
self.style = style
|
|
if substyle == "None":
|
|
substyle = None
|
|
self.substyle = substyle
|
|
self.style_id = style_id
|
|
|
|
|
|
class RecraftIO:
|
|
STYLEV3 = "RECRAFT_V3_STYLE"
|
|
SVG = "SVG" # TODO: if acceptable, move into ComfyUI's typing class
|
|
COLOR = "RECRAFT_COLOR"
|
|
CONTROLS = "RECRAFT_CONTROLS"
|
|
|
|
|
|
class RecraftStyleV3(str, Enum):
|
|
#any = 'any' NOTE: this does not work for some reason... why?
|
|
realistic_image = 'realistic_image'
|
|
digital_illustration = 'digital_illustration'
|
|
vector_illustration = 'vector_illustration'
|
|
logo_raster = 'logo_raster'
|
|
|
|
|
|
def get_v3_substyles(style_v3: str, include_none=True) -> list[str]:
|
|
substyles: list[str] = []
|
|
if include_none:
|
|
substyles.append("None")
|
|
return substyles + dict_recraft_substyles_v3.get(style_v3, [])
|
|
|
|
|
|
dict_recraft_substyles_v3 = {
|
|
RecraftStyleV3.realistic_image: [
|
|
"b_and_w",
|
|
"enterprise",
|
|
"evening_light",
|
|
"faded_nostalgia",
|
|
"forest_life",
|
|
"hard_flash",
|
|
"hdr",
|
|
"motion_blur",
|
|
"mystic_naturalism",
|
|
"natural_light",
|
|
"natural_tones",
|
|
"organic_calm",
|
|
"real_life_glow",
|
|
"retro_realism",
|
|
"retro_snapshot",
|
|
"studio_portrait",
|
|
"urban_drama",
|
|
"village_realism",
|
|
"warm_folk"
|
|
],
|
|
RecraftStyleV3.digital_illustration: [
|
|
"2d_art_poster",
|
|
"2d_art_poster_2",
|
|
"antiquarian",
|
|
"bold_fantasy",
|
|
"child_book",
|
|
"child_books",
|
|
"cover",
|
|
"crosshatch",
|
|
"digital_engraving",
|
|
"engraving_color",
|
|
"expressionism",
|
|
"freehand_details",
|
|
"grain",
|
|
"grain_20",
|
|
"graphic_intensity",
|
|
"hand_drawn",
|
|
"hand_drawn_outline",
|
|
"handmade_3d",
|
|
"hard_comics",
|
|
"infantile_sketch",
|
|
"long_shadow",
|
|
"modern_folk",
|
|
"multicolor",
|
|
"neon_calm",
|
|
"noir",
|
|
"nostalgic_pastel",
|
|
"outline_details",
|
|
"pastel_gradient",
|
|
"pastel_sketch",
|
|
"pixel_art",
|
|
"plastic",
|
|
"pop_art",
|
|
"pop_renaissance",
|
|
"seamless",
|
|
"street_art",
|
|
"tablet_sketch",
|
|
"urban_glow",
|
|
"urban_sketching",
|
|
"vanilla_dreams",
|
|
"young_adult_book",
|
|
"young_adult_book_2"
|
|
],
|
|
RecraftStyleV3.vector_illustration: [
|
|
"bold_stroke",
|
|
"chemistry",
|
|
"colored_stencil",
|
|
"contour_pop_art",
|
|
"cosmics",
|
|
"cutout",
|
|
"depressive",
|
|
"editorial",
|
|
"emotional_flat",
|
|
"engraving",
|
|
"infographical",
|
|
"line_art",
|
|
"line_circuit",
|
|
"linocut",
|
|
"marker_outline",
|
|
"mosaic",
|
|
"naivector",
|
|
"roundish_flat",
|
|
"seamless",
|
|
"segmented_colors",
|
|
"sharp_contrast",
|
|
"thin",
|
|
"vector_photo",
|
|
"vivid_shapes"
|
|
],
|
|
RecraftStyleV3.logo_raster: [
|
|
"emblem_graffiti",
|
|
"emblem_pop_art",
|
|
"emblem_punk",
|
|
"emblem_stamp",
|
|
"emblem_vintage"
|
|
],
|
|
}
|
|
|
|
|
|
class RecraftModel(str, Enum):
|
|
recraftv3 = 'recraftv3'
|
|
recraftv2 = 'recraftv2'
|
|
|
|
|
|
class RecraftImageSize(str, Enum):
|
|
res_1024x1024 = '1024x1024'
|
|
res_1365x1024 = '1365x1024'
|
|
res_1024x1365 = '1024x1365'
|
|
res_1536x1024 = '1536x1024'
|
|
res_1024x1536 = '1024x1536'
|
|
res_1820x1024 = '1820x1024'
|
|
res_1024x1820 = '1024x1820'
|
|
res_1024x2048 = '1024x2048'
|
|
res_2048x1024 = '2048x1024'
|
|
res_1434x1024 = '1434x1024'
|
|
res_1024x1434 = '1024x1434'
|
|
res_1024x1280 = '1024x1280'
|
|
res_1280x1024 = '1280x1024'
|
|
res_1024x1707 = '1024x1707'
|
|
res_1707x1024 = '1707x1024'
|
|
|
|
|
|
class RecraftColorObject(BaseModel):
|
|
rgb: list[int] = Field(..., description='An array of 3 integer values in range of 0...255 defining RGB Color Model')
|
|
|
|
|
|
class RecraftControlsObject(BaseModel):
|
|
colors: Optional[list[RecraftColorObject]] = Field(None, description='An array of preferable colors')
|
|
background_color: Optional[RecraftColorObject] = Field(None, description='Use given color as a desired background color')
|
|
no_text: Optional[bool] = Field(None, description='Do not embed text layouts')
|
|
artistic_level: Optional[conint(ge=0, le=5)] = Field(None, description='Defines artistic tone of your image. At a simple level, the person looks straight at the camera in a static and clean style. Dynamic and eccentric levels introduce movement and creativity. The value should be in range [0..5].')
|
|
|
|
|
|
class RecraftImageGenerationRequest(BaseModel):
|
|
prompt: str = Field(..., description='The text prompt describing the image to generate')
|
|
size: Optional[RecraftImageSize] = Field(None, description='The size of the generated image (e.g., "1024x1024")')
|
|
n: conint(ge=1, le=6) = Field(..., description='The number of images to generate')
|
|
negative_prompt: Optional[str] = Field(None, description='A text description of undesired elements on an image')
|
|
model: Optional[RecraftModel] = Field(RecraftModel.recraftv3, description='The model to use for generation (e.g., "recraftv3")')
|
|
style: Optional[str] = Field(None, description='The style to apply to the generated image (e.g., "digital_illustration")')
|
|
substyle: Optional[str] = Field(None, description='The substyle to apply to the generated image, depending on the style input')
|
|
controls: Optional[RecraftControlsObject] = Field(None, description='A set of custom parameters to tweak generation process')
|
|
style_id: Optional[str] = Field(None, description='Use a previously uploaded style as a reference; UUID')
|
|
strength: Optional[confloat(ge=0.0, le=1.0)] = Field(None, description='Defines the difference with the original image, should lie in [0, 1], where 0 means almost identical, and 1 means miserable similarity')
|
|
random_seed: Optional[int] = Field(None, description="Seed for video generation")
|
|
# text_layout
|
|
|
|
|
|
class RecraftReturnedObject(BaseModel):
|
|
image_id: str = Field(..., description='Unique identifier for the generated image')
|
|
url: str = Field(..., description='URL to access the generated image')
|
|
|
|
|
|
class RecraftImageGenerationResponse(BaseModel):
|
|
created: int = Field(..., description='Unix timestamp when the generation was created')
|
|
credits: int = Field(..., description='Number of credits used for the generation')
|
|
data: Optional[list[RecraftReturnedObject]] = Field(None, description='Array of generated image information')
|
|
image: Optional[RecraftReturnedObject] = Field(None, description='Single generated image')
|