Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Added descriptions to the pipeline parameters. #144

Merged
merged 4 commits into from
Aug 13, 2024
Merged

Added descriptions to the pipeline parameters. #144

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
6f40cc1
Added descriptions to the parameters.
EAsuperstar Aug 2, 2024
0b15207
The descriptions have been updated to better apply to the current imp…
EAsuperstar Aug 10, 2024
99404bb
refactor: shorten parameter descriptions
rickstaa Aug 13, 2024
2c0e341
chore: update OpenAPI spec and golang bindings
rickstaa Aug 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 8 additions & 4 deletions runner/app/routes/audio_to_text.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,7 @@
from app.dependencies import get_pipeline
from app.pipelines.base import Pipeline
from app.pipelines.utils.audio import AudioConversionError
from app.routes.util import (HTTPError, TextResponse, file_exceeds_max_size,
http_error)
from app.routes.util import HTTPError, TextResponse, file_exceeds_max_size, http_error
from fastapi import APIRouter, Depends, File, Form, UploadFile, status
from fastapi.responses import JSONResponse
from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
Expand Down Expand Up @@ -56,8 +55,13 @@ def handle_pipeline_error(e: Exception) -> JSONResponse:
include_in_schema=False,
)
async def audio_to_text(
audio: Annotated[UploadFile, File()],
model_id: Annotated[str, Form()] = "",
audio: Annotated[
UploadFile, File(description="Uploaded audio file to be transcribed.")
],
model_id: Annotated[
str,
Form(description="Hugging Face model ID used for transcription."),
] = "",
pipeline: Pipeline = Depends(get_pipeline),
token: HTTPAuthorizationCredentials = Depends(HTTPBearer(auto_error=False)),
):
Expand Down
65 changes: 52 additions & 13 deletions runner/app/routes/image_to_image.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,7 @@

from app.dependencies import get_pipeline
from app.pipelines.base import Pipeline
from app.routes.util import (HTTPError, ImageResponse, http_error,
image_to_data_url)
from app.routes.util import HTTPError, ImageResponse, http_error, image_to_data_url
from fastapi import APIRouter, Depends, File, Form, UploadFile, status
from fastapi.responses import JSONResponse
from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
Expand Down Expand Up @@ -36,19 +35,59 @@
include_in_schema=False,
)
async def image_to_image(
prompt: Annotated[str, Form()],
image: Annotated[UploadFile, File()],
model_id: Annotated[str, Form()] = "",
strength: Annotated[float, Form()] = 0.8,
guidance_scale: Annotated[float, Form()] = 7.5,
image_guidance_scale: Annotated[float, Form()] = 1.5,
negative_prompt: Annotated[str, Form()] = "",
safety_check: Annotated[bool, Form()] = True,
seed: Annotated[int, Form()] = None,
prompt: Annotated[
str,
Form(description="Text prompt(s) to guide image generation."),
],
image: Annotated[
UploadFile,
File(description="Uploaded image to modify with the pipeline."),
],
model_id: Annotated[
str,
Form(description="Hugging Face model ID used for image generation."),
] = "",
strength: Annotated[
float,
Form(
description="Degree of transformation applied to the reference image (0 to 1)."
),
] = 0.8,
guidance_scale: Annotated[
float,
Form(
description="Encourages model to generate images closely linked to the text prompt (higher values may reduce image quality)."
),
] = 7.5,
image_guidance_scale: Annotated[
float,
Form(
description="Degree to which the generated image is pushed towards the initial image."
),
] = 1.5,
negative_prompt: Annotated[
str,
Form(
description="Text prompt(s) to guide what to exclude from image generation. Ignored if guidance_scale < 1."
),
] = "",
safety_check: Annotated[
bool,
Form(
description="Perform a safety check to estimate if generated images could be offensive or harmful."
),
] = True,
seed: Annotated[int, Form(description="Seed for random number generation.")] = None,
num_inference_steps: Annotated[
int, Form()
int,
Form(
description="Number of denoising steps. More steps usually lead to higher quality images but slower inference. Modulated by strength."
),
] = 100, # NOTE: Hardcoded due to varying pipeline values.
num_images_per_prompt: Annotated[int, Form()] = 1,
num_images_per_prompt: Annotated[
int,
Form(description="Number of images to generate per prompt."),
] = 1,
pipeline: Pipeline = Depends(get_pipeline),
token: HTTPAuthorizationCredentials = Depends(HTTPBearer(auto_error=False)),
):
Expand Down
52 changes: 40 additions & 12 deletions runner/app/routes/image_to_video.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,7 @@

from app.dependencies import get_pipeline
from app.pipelines.base import Pipeline
from app.routes.util import (HTTPError, VideoResponse, http_error,
image_to_data_url)
from app.routes.util import HTTPError, VideoResponse, http_error, image_to_data_url
from fastapi import APIRouter, Depends, File, Form, UploadFile, status
from fastapi.responses import JSONResponse
from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
Expand Down Expand Up @@ -35,17 +34,46 @@
include_in_schema=False,
)
async def image_to_video(
image: Annotated[UploadFile, File()],
model_id: Annotated[str, Form()] = "",
height: Annotated[int, Form()] = 576,
width: Annotated[int, Form()] = 1024,
fps: Annotated[int, Form()] = 6,
motion_bucket_id: Annotated[int, Form()] = 127,
noise_aug_strength: Annotated[float, Form()] = 0.02,
seed: Annotated[int, Form()] = None,
safety_check: Annotated[bool, Form()] = True,
image: Annotated[
UploadFile,
File(description="Uploaded image to generate a video from."),
],
model_id: Annotated[
str, Form(description="Hugging Face model ID used for video generation.")
] = "",
height: Annotated[
int, Form(description="The height in pixels of the generated video.")
] = 576,
width: Annotated[
int, Form(description="The width in pixels of the generated video.")
] = 1024,
fps: Annotated[
int, Form(description="The frames per second of the generated video.")
] = 6,
motion_bucket_id: Annotated[
int,
Form(
description="Used for conditioning the amount of motion for the generation. The higher the number the more motion will be in the video."
),
] = 127,
noise_aug_strength: Annotated[
float,
Form(
description="Amount of noise added to the conditioning image. Higher values reduce resemblance to the conditioning image and increase motion."
),
] = 0.02,
safety_check: Annotated[
bool,
Form(
description="Perform a safety check to estimate if generated images could be offensive or harmful."
),
] = True,
seed: Annotated[int, Form(description="Seed for random number generation.")] = None,
num_inference_steps: Annotated[
int, Form()
int,
Form(
description="Number of denoising steps. More steps usually lead to higher quality images but slower inference. Modulated by strength."
),
] = 25, # NOTE: Hardcoded due to varying pipeline values.
pipeline: Pipeline = Depends(get_pipeline),
token: HTTPAuthorizationCredentials = Depends(HTTPBearer(auto_error=False)),
Expand Down
65 changes: 53 additions & 12 deletions runner/app/routes/text_to_image.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,7 @@

from app.dependencies import get_pipeline
from app.pipelines.base import Pipeline
from app.routes.util import (HTTPError, ImageResponse, http_error,
image_to_data_url)
from app.routes.util import HTTPError, ImageResponse, http_error, image_to_data_url
from fastapi import APIRouter, Depends, status
from fastapi.responses import JSONResponse
from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
Expand All @@ -22,17 +21,59 @@ class TextToImageParams(BaseModel):
# supports OAPI 3.1 https://github.com/deepmap/oapi-codegen/issues/373
model_id: Annotated[
str,
Field(default="", description=""),
Field(
default="", description="Hugging Face model ID used for image generation."
),
]
prompt: Annotated[
str,
Field(
description="Text prompt(s) to guide image generation. Separate multiple prompts with '|' if supported by the model."
),
]
height: Annotated[
int,
Field(default=576, description="The height in pixels of the generated image."),
]
width: Annotated[
int,
Field(default=1024, description="The width in pixels of the generated image."),
]
guidance_scale: Annotated[
float,
Field(
default=7.5,
description="Encourages model to generate images closely linked to the text prompt (higher values may reduce image quality).",
),
]
negative_prompt: Annotated[
str,
Field(
default="",
description="Text prompt(s) to guide what to exclude from image generation. Ignored if guidance_scale < 1.",
),
]
safety_check: Annotated[
bool,
Field(
default=True,
description="Perform a safety check to estimate if generated images could be offensive or harmful.",
),
]
seed: Annotated[
int, Field(default=None, description="Seed for random number generation.")
]
num_inference_steps: Annotated[
int,
Field(
default=50,
description="Number of denoising steps. More steps usually lead to higher quality images but slower inference. Modulated by strength.",
),
]
num_images_per_prompt: Annotated[
int,
Field(default=1, description="Number of images to generate per prompt."),
]
prompt: Annotated[str, Field(description="")]
height: Annotated[int, Field(default=576, description="")]
width: Annotated[int, Field(default=1024, description="")]
guidance_scale: Annotated[float, Field(default=7.5, description="")]
negative_prompt: Annotated[str, Field(default="", description="")]
safety_check: Annotated[bool, Field(default=True, description="")]
seed: Annotated[int, Field(default=None, description="")]
num_inference_steps: Annotated[int, Field(default=50, description="")]
num_images_per_prompt: Annotated[int, Field(default=1, description="")]


RESPONSES = {
Expand Down
32 changes: 24 additions & 8 deletions runner/app/routes/upscale.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,7 @@

from app.dependencies import get_pipeline
from app.pipelines.base import Pipeline
from app.routes.util import (HTTPError, ImageResponse, http_error,
image_to_data_url)
from app.routes.util import HTTPError, ImageResponse, http_error, image_to_data_url
from fastapi import APIRouter, Depends, File, Form, UploadFile, status
from fastapi.responses import JSONResponse
from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
Expand Down Expand Up @@ -36,13 +35,30 @@
include_in_schema=False,
)
async def upscale(
prompt: Annotated[str, Form()],
image: Annotated[UploadFile, File()],
model_id: Annotated[str, Form()] = "",
safety_check: Annotated[bool, Form()] = True,
seed: Annotated[int, Form()] = None,
prompt: Annotated[
str,
Form(description="Text prompt(s) to guide upscaled image generation."),
],
image: Annotated[
UploadFile,
File(description="Uploaded image to modify with the pipeline."),
],
model_id: Annotated[
str,
Form(description="Hugging Face model ID used for upscaled image generation."),
] = "",
safety_check: Annotated[
bool,
Form(
description="Perform a safety check to estimate if generated images could be offensive or harmful."
),
] = True,
seed: Annotated[int, Form(description="Seed for random number generation.")] = None,
num_inference_steps: Annotated[
int, Form()
int,
Form(
description="Number of denoising steps. More steps usually lead to higher quality images but slower inference. Modulated by strength."
),
] = 75, # NOTE: Hardcoded due to varying pipeline values.
pipeline: Pipeline = Depends(get_pipeline),
token: HTTPAuthorizationCredentials = Depends(HTTPBearer(auto_error=False)),
Expand Down
Loading