nodes/Bria-AI-ComfyUI-BRIA-API
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'main' into WAI-4253

Browse Source
This commit is contained in:
Yazan Numoor
2025-12-16 17:11:53 +02:00
committed by GitHub
parent 82f31ddf72 8f7edd926d
commit 855ed814ed
12 changed files with 1829 additions and 421 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Readme.md
+40 -15
View File
@@ -31,28 +31,53 @@ To load a workflow, import the compatible workflow.json files from this [folder]
## Image Generation Nodes
These nodes allow you to leverage Bria's image generation capabilities within ComfyUI. We offer our latest **V2 nodes** designed for precise control via structured prompts (currently powered by the **FIBO** model), alongside our **V1 nodes** for various established pipelines.
These nodes allow you to leverage Bria's image generation capabilities within ComfyUI. We offer our latest **V2 nodes** (powered by the **FIBO** model) for precise control via structured prompts, alongside our legacy **V1 nodes**.
### V2 Generation Nodes
### V2 Generation Nodes (FIBO)
These nodes generate images based on detailed **structured prompts** for enhanced control and consistency. They are currently powered by the state-of-the-art **FIBO** text-to-image model.
Our V2 nodes utilize a state-of-the-art **two-step process** for enhanced control and consistency:
| **Node** | **Description** |
| --- | --- |
| **Generate Image** | Creates new images from text or image inputs. Internally translates the input into a structured prompt using a selected VLM bridge before generating with the image model. |
| **Refine and Regenerate Image** | Refines a generated image using a provided `structured_prompt` (from a previous generation) and a refinement text prompt. |
- **Translation**: A VLM Bridge translates your input (prompt/images) into a machine-readable `structured_prompt` (JSON).
- **Generation**: The FIBO model generates the final image based on that specific JSON.
### V1 Generation Nodes
**Available Versions:**
- **Regular**: Uses **Gemini 2.5 Flash** as the bridge for state-of-the-art, detailed prompt creation.
- **Lite**: Uses **FIBO-VLM** (Bria's open-source bridge) for faster, flexible, or on-prem deployment.
**Available V2 Nodes & Input Rules**
We offer three distinct nodes to give you full control over this pipeline:
1. **Structured Prompt Bridge**
- Outputs a JSON string only (no image).
- This node decouples the "intent translation" step from generation. It is ideal for "human-in-the-loop" workflows where you want to inspect, audit, or version-control the JSON instructions before generating.
- **Supported Input Combinations:**
- `prompt`: Generates a structured prompt from text.
- `images`: Generates a structured prompt based on an input image.
- `images + prompt`: Generates a structured prompt based on an image, guided by text.
- `structured_prompt + prompt`: Updates an existing structured prompt using new text instructions (outputs updated JSON).
2. **Generate Image**
- Outputs an Image.
- The primary node for generation. It automatically handles translation and generation in one go, or accepts a pre-made structured prompt for reproducible results.
- **Supported Input Combinations:**
- `prompt`: Generates a new image from text.
- `images`: Generates a new image inspired by a reference image.
- `images + prompt`: Generates a new image inspired by an image and guided by text.
- `structured_prompt`: Recreates a previous image exactly (when combined with a seed).
3. **Refine and Regenerate**
- Outputs a Refined Image.
- This node allows you to take a result you like and tweak it without losing the original composition.
- **Supported Input Combination:**
- `structured_prompt + prompt`: Refines a previous image using new text instructions (combined with a seed) to adjust details while maintaining consistency.
### V1 Generation Nodes (Legacy)
These nodes utilize Bria's previous generation pipeline. While V2 is recommended for the highest control and quality, V1 remains available for backward compatibility with established workflows.
These nodes create high-quality images using Bria's V1 pipelines, supporting various aspect ratios and styles.
| Node | Description |
|------------------------|--------------------------------------------------------------------|
| **Text2Image Base** | Generates images from text prompts, serving as the foundation for text-based image creation. |
| **Text2Image Fast** | Optimized for speed, this node generates images from text prompts with faster results while maintaining quality. |
| **Text2Image HD** | Optimized for high-resolution outputs, this node generates detailed and sharp visuals from text prompts. |
| **Reimagine** | Guides image generation using both prompts and an input image. Preserve the original structure and depth while introducing new materials, colors, and textures. |
## Tailored Generation Nodes
These nodes use pre-trained tailored models to generate images that faithfully reproduce specific visual IP elements or guidelines.
__init__.py
+14
View File
@@ -15,7 +15,11 @@ from .nodes import (
TailoredPortraitNode,
ReimagineNode,
GenerateImageNodeV2,
GenerateImageLiteNodeV2,
RefineImageNodeV2,
RefineImageLiteNodeV2,
GenerateStructuredPromptNodeV2,
GenerateStructuredPromptLiteNodeV2,
ShotByTextAutomaticNode,
ShotByImageManualPaddingNode,
ShotByImageAutomaticAspectRatioNode,
@@ -66,7 +70,11 @@ NODE_CLASS_MAPPINGS = {
"ReimagineNode": ReimagineNode,
"AttributionByImageNode": AttributionByImageNode,
"GenerateImageNodeV2": GenerateImageNodeV2,
"GenerateImageLiteNodeV2": GenerateImageLiteNodeV2,
"RefineImageNodeV2": RefineImageNodeV2,
"RefineImageLiteNodeV2": RefineImageLiteNodeV2,
"GenerateStructuredPromptNodeV2": GenerateStructuredPromptNodeV2,
"GenerateStructuredPromptLiteNodeV2": GenerateStructuredPromptLiteNodeV2,
"RemoveVideoBackgroundNode":RemoveVideoBackgroundNode,
"VideoSolidColorBackgroundNode":VideoSolidColorBackgroundNode,
"VideoMaskByPromptNode":VideoMaskByPromptNode,
@@ -105,7 +113,11 @@ NODE_DISPLAY_NAME_MAPPINGS = {
"ReimagineNode": "Bria Reimagine",
"AttributionByImageNode": "Attribution By Image Node",
"GenerateImageNodeV2": "Generate Image",
"GenerateImageLiteNodeV2": "Generate Image - Lite",
"RefineImageNodeV2": "Refine and Regenerate Image",
"RefineImageLiteNodeV2": "Refine Image - Lite",
"GenerateStructuredPromptNodeV2": "Generate Structured Prompt",
"GenerateStructuredPromptLiteNodeV2": "Generate Structured Prompt - Lite",
"RemoveVideoBackgroundNode": "Bria Remove Video Background",
"VideoSolidColorBackgroundNode":"Bria SolidColor Background Video",
"VideoMaskByPromptNode":"Bria Video Mask By Prompt",
@@ -115,3 +127,5 @@ NODE_DISPLAY_NAME_MAPPINGS = {
"LoadVideoFramesNode":"Bria Load Video",
"PreviewVideoURLNode":"Bria Preview Video"
}
nodes/__init__.py
+4
View File
@@ -12,7 +12,11 @@ from .text_2_image_fast_node import Text2ImageFastNode
from .text_2_image_hd_node import Text2ImageHDNode
from .reimagine_node import ReimagineNode
from .generate_image_node_v2 import GenerateImageNodeV2
from .generate_image_lite_node_v2 import GenerateImageLiteNodeV2
from .refine_image_node_v2 import RefineImageNodeV2
from .refine_image_lite_node_v2 import RefineImageLiteNodeV2
from .generate_structured_prompt_node_v2 import GenerateStructuredPromptNodeV2
from .generate_structured_prompt_lite_node_v2 import GenerateStructuredPromptLiteNodeV2
from .shot_by_text_node import ShotByTextOriginalNode
from .shot_by_text_automatic_aspect_ratio_node import ShotByTextAutomaticAspectRatioNode
from .shot_by_text_automatic_node import ShotByTextAutomaticNode
nodes/generate_image_lite_node_v2.py
+151
View File
@@ -0,0 +1,151 @@
import requests
import torch
from .common import (
deserialize_and_get_comfy_key,
postprocess_image,
preprocess_image,
image_to_base64,
poll_status_until_completed,
)
class GenerateImageLiteNodeV2:
"""Lite Image Generation Node"""
api_url = "https://engine.prod.bria-api.com/v2/image/generate/lite"
@classmethod
def INPUT_TYPES(cls):
return {
"required": {
"api_token": ("STRING", {"default": "BRIA_API_TOKEN"}),
"prompt": ("STRING",),
},
"optional": {
"model_version": (["FIBO"], {"default": "FIBO"}),
"structured_prompt": ("STRING", {"default": ""}),
"images": ("IMAGE",),
"aspect_ratio": (
["1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9"],
{"default": "1:1"},
),
"steps_num": (
"INT",
{
"default": 8,
"min": 8,
"max": 30,
},
),
"guidance_scale": (
"INT",
{
"default": 5,
"min": 3,
"max": 5,
},
),
"seed": ("INT", {"default": 123456}),
},
}
RETURN_TYPES = ("IMAGE", "STRING", "INT")
RETURN_NAMES = ("image", "structured_prompt", "seed")
CATEGORY = "API Nodes"
FUNCTION = "execute"
def _validate_token(self, api_token: str):
if api_token.strip() == "" or api_token.strip() == "BRIA_API_TOKEN":
raise Exception("Please insert a valid API token.")
def _build_payload(
self,
prompt,
model_version,
structured_prompt,
aspect_ratio,
steps_num,
guidance_scale,
seed,
images=None,
):
payload = {
"prompt": prompt,
"model_version": model_version,
"aspect_ratio": aspect_ratio,
"steps_num": steps_num,
"guidance_scale": guidance_scale,
"seed": seed,
}
if structured_prompt:
payload["structured_prompt"] = structured_prompt
if images is not None:
if isinstance(images, torch.Tensor):
preprocess_images = preprocess_image(images)
payload["images"] = [image_to_base64(preprocess_images)]
return payload
def execute(
self,
api_token,
prompt,
model_version,
structured_prompt,
aspect_ratio,
steps_num,
guidance_scale,
seed,
images=None,
):
self._validate_token(api_token)
payload = self._build_payload(
prompt,
model_version,
structured_prompt,
aspect_ratio,
steps_num,
guidance_scale,
seed,
images,
)
api_token = deserialize_and_get_comfy_key(api_token)
headers = {"Content-Type": "application/json", "api_token": api_token}
try:
response = requests.post(self.api_url, json=payload, headers=headers)
if response.status_code in (200, 202):
print(
f"Initial request successful to {self.api_url}, polling for completion..."
)
response_dict = response.json()
status_url = response_dict.get("status_url")
request_id = response_dict.get("request_id")
if not status_url:
raise Exception("No status_url returned from API")
print(f"Request ID: {request_id}, Status URL: {status_url}")
final_response = poll_status_until_completed(status_url, api_token)
result = final_response.get("result", {})
result_image_url = result.get("image_url")
structured_prompt = result.get("structured_prompt", "")
used_seed = result.get("seed")
image_response = requests.get(result_image_url)
result_image = postprocess_image(image_response.content)
return (result_image, structured_prompt, used_seed)
raise Exception(
f"Error: API request failed with status code {response.status_code} {response.text}"
)
except Exception as e:
raise Exception(f"{e}")
nodes/generate_image_node_v2.py
+32 -18
View File
@@ -10,10 +10,10 @@ from .common import (
)
class _BaseGenerateImageNodeV2:
"""Base class for image generation nodes (standard & pro)."""
class GenerateImageNodeV2:
"""Standard Image Generation Node"""
api_url = None # Each subclass must define its API endpoint
api_url = "https://engine.prod.bria-api.com/v2/image/generate"
@classmethod
def INPUT_TYPES(cls):
@@ -24,14 +24,29 @@ class _BaseGenerateImageNodeV2:
},
"optional": {
"model_version": (["FIBO"], {"default": "FIBO"}),
"negative_prompt": ("STRING", {"default": ""}),
"structured_prompt": ("STRING", {"default": ""}),
"negative_prompt": ("STRING",),
"images": ("IMAGE",),
"aspect_ratio": (
["1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9"],
{"default": "1:1"},
),
"steps_num": ("INT", {"default": 50, "min": 20, "max": 50}),
"guidance_scale": ("INT", {"default": 5, "min": 3, "max": 5}),
"steps_num": (
"INT",
{
"default": 50,
"min": 35,
"max": 50,
},
),
"guidance_scale": (
"INT",
{
"default": 5,
"min": 3,
"max": 5,
},
),
"seed": ("INT", {"default": 123456}),
},
}
@@ -41,6 +56,7 @@ class _BaseGenerateImageNodeV2:
CATEGORY = "API Nodes"
FUNCTION = "execute"
def _validate_token(self, api_token: str):
if api_token.strip() == "" or api_token.strip() == "BRIA_API_TOKEN":
raise Exception("Please insert a valid API token.")
@@ -49,29 +65,31 @@ class _BaseGenerateImageNodeV2:
self,
prompt,
model_version,
negative_prompt,
structured_prompt,
aspect_ratio,
steps_num,
guidance_scale,
seed,
negative_prompt=None,
images=None,
):
payload = {
"prompt": prompt,
"model_version": model_version,
"negative_prompt": negative_prompt,
"aspect_ratio": aspect_ratio,
"steps_num": steps_num,
"guidance_scale": guidance_scale,
"seed": seed,
"negative_prompt":negative_prompt
}
if structured_prompt:
payload["structured_prompt"] = structured_prompt
if images is not None:
if isinstance(images, torch.Tensor):
preprocess_images = preprocess_image(images)
payload["images"] = [image_to_base64(preprocess_images)]
return payload
def execute(
@@ -79,22 +97,24 @@ class _BaseGenerateImageNodeV2:
api_token,
prompt,
model_version,
negative_prompt,
structured_prompt,
aspect_ratio,
steps_num,
guidance_scale,
seed,
negative_prompt=None,
images=None,
):
self._validate_token(api_token)
payload = self._build_payload(
prompt,
model_version,
negative_prompt,
structured_prompt,
aspect_ratio,
steps_num,
guidance_scale,
seed,
negative_prompt,
images,
)
api_token = deserialize_and_get_comfy_key(api_token)
@@ -134,10 +154,4 @@ class _BaseGenerateImageNodeV2:
)
except Exception as e:
raise Exception(f"{e}")
class GenerateImageNodeV2(_BaseGenerateImageNodeV2):
"""Standard Image Generation Node"""
def __init__(self):
self.api_url = "https://engine.prod.bria-api.com/v2/image/generate"
raise Exception(f"{e}")
nodes/generate_structured_prompt_lite_node_v2.py
+106
View File
@@ -0,0 +1,106 @@
import requests
from .common import (
deserialize_and_get_comfy_key,
image_to_base64,
poll_status_until_completed,
preprocess_image,
)
import torch
class GenerateStructuredPromptLiteNodeV2:
"""Lite Structured Prompt Generation Node"""
api_url = "https://engine.prod.bria-api.com/v2/structured_prompt/generate/lite"
@classmethod
def INPUT_TYPES(cls):
return {
"required": {
"api_token": ("STRING", {"default": "BRIA_API_TOKEN"}),
"prompt": ("STRING",),
},
"optional": {
"structured_prompt": ("STRING",),
"images": ("IMAGE",),
"seed": ("INT", {"default": 123456}),
},
}
RETURN_TYPES = ("STRING", "INT")
RETURN_NAMES = ("structured_prompt", "seed")
CATEGORY = "API Nodes"
FUNCTION = "execute"
def _validate_token(self, api_token: str):
if api_token.strip() == "" or api_token.strip() == "BRIA_API_TOKEN":
raise Exception("Please insert a valid API token.")
def _build_payload(
self,
prompt,
seed,
structured_prompt,
images=None
):
payload = {
"prompt": prompt,
"seed": seed,
}
if structured_prompt:
payload["structured_prompt"] = structured_prompt
if images is not None:
if isinstance(images, torch.Tensor):
preprocess_images = preprocess_image(images)
payload["images"] = [image_to_base64(preprocess_images)]
return payload
def execute(
self,
api_token,
prompt,
seed,
structured_prompt,
images=None,
):
self._validate_token(api_token)
payload = self._build_payload(
prompt,
seed,
structured_prompt,
images
)
api_token = deserialize_and_get_comfy_key(api_token)
headers = {"Content-Type": "application/json", "api_token": api_token}
try:
response = requests.post(self.api_url, json=payload, headers=headers)
if response.status_code in (200, 202):
print(
f"Initial request successful to {self.api_url}, polling for completion..."
)
response_dict = response.json()
status_url = response_dict.get("status_url")
request_id = response_dict.get("request_id")
if not status_url:
raise Exception("No status_url returned from API")
print(f"Request ID: {request_id}, Status URL: {status_url}")
final_response = poll_status_until_completed(status_url, api_token)
result = final_response.get("result", {})
structured_prompt = result.get("structured_prompt", "")
used_seed = result.get("seed", seed)
return (structured_prompt, used_seed)
raise Exception(
f"Error: API request failed with status code {response.status_code} {response.text}"
)
except Exception as e:
raise Exception(f"{e}")
nodes/generate_structured_prompt_node_v2.py
+105
View File
@@ -0,0 +1,105 @@
import requests
from .common import (
deserialize_and_get_comfy_key,
image_to_base64,
poll_status_until_completed,
preprocess_image,
)
import torch
class GenerateStructuredPromptNodeV2:
"""Standard Structured Prompt Generation Node"""
api_url = "https://engine.prod.bria-api.com/v2/structured_prompt/generate"
@classmethod
def INPUT_TYPES(cls):
return {
"required": {
"api_token": ("STRING", {"default": "BRIA_API_TOKEN"}),
"prompt": ("STRING",),
},
"optional": {
"structured_prompt": ("STRING",),
"images": ("IMAGE",),
"seed": ("INT", {"default": 123456}),
},
}
RETURN_TYPES = ("STRING", "INT")
RETURN_NAMES = ("structured_prompt", "seed")
CATEGORY = "API Nodes"
FUNCTION = "execute"
def _validate_token(self, api_token: str):
if api_token.strip() == "" or api_token.strip() == "BRIA_API_TOKEN":
raise Exception("Please insert a valid API token.")
def _build_payload(
self,
prompt,
seed,
structured_prompt,
images=None
):
payload = {
"prompt": prompt,
"seed": seed,
}
if structured_prompt:
payload["structured_prompt"] = structured_prompt
if images is not None:
if isinstance(images, torch.Tensor):
preprocess_images = preprocess_image(images)
payload["images"] = [image_to_base64(preprocess_images)]
return payload
def execute(
self,
api_token,
prompt,
seed,
structured_prompt,
images=None,
):
self._validate_token(api_token)
payload = self._build_payload(
prompt,
seed,
structured_prompt,
images
)
api_token = deserialize_and_get_comfy_key(api_token)
headers = {"Content-Type": "application/json", "api_token": api_token}
try:
response = requests.post(self.api_url, json=payload, headers=headers)
if response.status_code in (200, 202):
print(
f"Initial request successful to {self.api_url}, polling for completion..."
)
response_dict = response.json()
status_url = response_dict.get("status_url")
request_id = response_dict.get("request_id")
if not status_url:
raise Exception("No status_url returned from API")
print(f"Request ID: {request_id}, Status URL: {status_url}")
final_response = poll_status_until_completed(status_url, api_token)
result = final_response.get("result", {})
structured_prompt = result.get("structured_prompt", "")
used_seed = result.get("seed", seed)
return (structured_prompt, used_seed)
raise Exception(
f"Error: API request failed with status code {response.status_code} {response.text}"
)
except Exception as e:
raise Exception(f"{e}")
nodes/refine_image_lite_node_v2.py
+167
View File
@@ -0,0 +1,167 @@
import requests
from .common import deserialize_and_get_comfy_key, poll_status_until_completed, postprocess_image
class RefineImageLiteNodeV2:
"""Lite Refine Image Node"""
api_url = "https://engine.prod.bria-api.com/v2/structured_prompt/generate/lite"
generate_api_url = "https://engine.prod.bria-api.com/v2/image/generate/lite"
@classmethod
def INPUT_TYPES(cls):
return {
"required": {
"api_token": ("STRING", {"default": "BRIA_API_TOKEN"}),
"prompt": ("STRING",),
"structured_prompt": ("STRING",),
},
"optional": {
"model_version": (["FIBO"], {"default": "FIBO"}),
"aspect_ratio": (
["1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9"],
{"default": "1:1"},
),
"steps_num": (
"INT",
{
"default": 8,
"min": 8,
"max": 30,
},
),
"guidance_scale": (
"INT",
{
"default": 5,
"min": 3,
"max": 5,
},
),
"seed": ("INT", {"default": 123456}),
},
}
RETURN_TYPES = ("IMAGE", "STRING", "INT")
RETURN_NAMES = ("image", "structured_prompt", "seed")
CATEGORY = "API Nodes"
FUNCTION = "execute"
def _validate_token(self, api_token: str):
if api_token.strip() == "" or api_token.strip() == "BRIA_API_TOKEN":
raise Exception("Please insert a valid API token.")
def _build_payload(
self,
prompt,
structured_prompt,
model_version,
aspect_ratio,
steps_num,
guidance_scale,
seed,
):
payload = {
"prompt": prompt,
"model_version": model_version,
"aspect_ratio": aspect_ratio,
"steps_num": steps_num,
"guidance_scale": guidance_scale,
"seed": seed,
}
if structured_prompt:
payload["structured_prompt"] = structured_prompt
return payload
def execute(
self,
api_token,
prompt,
structured_prompt,
model_version,
aspect_ratio,
steps_num,
guidance_scale,
seed
):
self._validate_token(api_token)
payload = self._build_payload(
prompt,
structured_prompt,
model_version,
aspect_ratio,
steps_num,
guidance_scale,
seed,
)
api_token = deserialize_and_get_comfy_key(api_token)
headers = {"Content-Type": "application/json", "api_token": api_token}
try:
response = requests.post(self.api_url, json=payload, headers=headers)
if response.status_code in (200, 202):
print(f"Initial refine request successful to {self.api_url}, polling for completion...")
response_dict = response.json()
status_url = response_dict.get("status_url")
request_id = response_dict.get("request_id")
if not status_url:
raise Exception("No status_url returned from API")
print(f"Request ID: {request_id}, Status URL: {status_url}")
final_response = poll_status_until_completed(status_url, api_token)
result = final_response.get("result", {})
structured_prompt = result.get("structured_prompt", "")
used_seed = result.get("seed", seed)
# Step 2 to call genearte image
payloadForImageGenetrate = {
"prompt": prompt,
"structured_prompt":structured_prompt,
"model_version": model_version,
"aspect_ratio": aspect_ratio,
"steps_num": steps_num,
"guidance_scale": guidance_scale,
"seed": used_seed,
}
headers = {"Content-Type": "application/json", "api_token": api_token}
response = requests.post(self.generate_api_url, json=payloadForImageGenetrate, headers=headers)
if response.status_code in (200, 202):
print(
f"Initial request successful to {self.generate_api_url}, polling for completion..."
)
response_dict = response.json()
status_url = response_dict.get("status_url")
request_id = response_dict.get("request_id")
if not status_url:
raise Exception("No status_url returned from API")
print(f"Request ID: {request_id}, Status URL: {status_url}")
final_response = poll_status_until_completed(status_url, api_token)
result = final_response.get("result", {})
result_image_url = result.get("image_url")
structured_prompt = result.get("structured_prompt", "")
used_seed = result.get("seed")
image_response = requests.get(result_image_url)
result_image = postprocess_image(image_response.content)
return (result_image, structured_prompt, used_seed)
raise Exception(
f"Error: API request failed with status code {response.status_code} {response.text}"
)
except Exception as e:
raise Exception(f"{e}")
nodes/refine_image_node_v2.py
+30 -22
View File
@@ -2,12 +2,11 @@ import requests
from .common import deserialize_and_get_comfy_key, poll_status_until_completed, postprocess_image
class _BaseRefineImageNodeV2:
"""Base class for refine image nodes (standard & pro)."""
api_url = None # Must be overridden by subclasses
generate_api_url = None
class RefineImageNodeV2:
"""Standard Refine Image Node"""
api_url = "https://engine.prod.bria-api.com/v2/structured_prompt/generate" # Must be overridden by subclasses
generate_api_url = "https://engine.prod.bria-api.com/v2/image/generate"
@classmethod
def INPUT_TYPES(cls):
return {
@@ -18,17 +17,32 @@ class _BaseRefineImageNodeV2:
},
"optional": {
"model_version": (["FIBO"], {"default": "FIBO"}),
"negative_prompt": ("STRING", {"default": ""}),
"aspect_ratio": (
["1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9"],
{"default": "1:1"},
),
"steps_num": ("INT", {"default": 50, "min": 20, "max": 50}),
"guidance_scale": ("INT", {"default": 5, "min": 3, "max": 5}),
"steps_num": (
"INT",
{
"default": 50,
"min": 35,
"max": 50,
},
),
"guidance_scale": (
"INT",
{
"default": 5,
"min": 3,
"max": 5,
},
),
"seed": ("INT", {"default": 123456}),
"negative_prompt": ("STRING", {"default": ""}),
},
}
RETURN_TYPES = ("IMAGE", "STRING", "INT")
RETURN_NAMES = ("image", "structured_prompt", "seed")
CATEGORY = "API Nodes"
@@ -43,22 +57,23 @@ class _BaseRefineImageNodeV2:
prompt,
structured_prompt,
model_version,
negative_prompt,
aspect_ratio,
steps_num,
guidance_scale,
seed,
):
return {
payload = {
"prompt": prompt,
"model_version": model_version,
"negative_prompt": negative_prompt,
"aspect_ratio": aspect_ratio,
"steps_num": steps_num,
"guidance_scale": guidance_scale,
"seed": seed,
"structured_prompt": structured_prompt,
}
if structured_prompt:
payload["structured_prompt"] = structured_prompt
return payload
def execute(
self,
@@ -66,18 +81,17 @@ class _BaseRefineImageNodeV2:
prompt,
structured_prompt,
model_version,
negative_prompt,
aspect_ratio,
steps_num,
guidance_scale,
seed,
negative_prompt=None,
):
self._validate_token(api_token)
payload = self._build_payload(
prompt,
structured_prompt,
model_version,
negative_prompt,
aspect_ratio,
steps_num,
guidance_scale,
@@ -111,12 +125,13 @@ class _BaseRefineImageNodeV2:
"prompt": prompt,
"structured_prompt":structured_prompt,
"model_version": model_version,
"negative_prompt": negative_prompt,
"aspect_ratio": aspect_ratio,
"steps_num": steps_num,
"guidance_scale": guidance_scale,
"seed": used_seed,
"negative_prompt":negative_prompt
}
headers = {"Content-Type": "application/json", "api_token": api_token}
response = requests.post(self.generate_api_url, json=payloadForImageGenetrate, headers=headers)
@@ -152,10 +167,3 @@ class _BaseRefineImageNodeV2:
except Exception as e:
raise Exception(f"{e}")
class RefineImageNodeV2(_BaseRefineImageNodeV2):
"""Standard Refine Image Node"""
def __init__(self):
self.api_url = "https://engine.prod.bria-api.com/v2/structured_prompt/generate"
self.generate_api_url = "https://engine.prod.bria-api.com/v2/image/generate"
pyproject.toml
+1 -1
View File
@@ -1,7 +1,7 @@
[project]
name = "comfyui-bria-api"
description = "Custom nodes for ComfyUI using BRIA's API."
version = "2.1.8"
version = "2.1.10"
license = {file = "LICENSE"}
[project.urls]
workflows/generate_image_fibo-lite_workflow.json
+661
View File
@@ -0,0 +1,661 @@
{
"id": "1c31a92d-1e48-46b0-b4ad-60d537260922",
"revision": 0,
"last_node_id": 27,
"last_link_id": 46,
"nodes": [
{
"id": 5,
"type": "PreviewImage",
"pos": [
1235.1895751953125,
10.958272933959961
],
"size": [
140,
26
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 43
}
],
"outputs": [],
"properties": {
"Node name for S&R": "PreviewImage"
},
"widgets_values": []
},
{
"id": 6,
"type": "PreviewImage",
"pos": [
774.4347534179688,
-58.6872444152832
],
"size": [
140,
26
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 29
}
],
"outputs": [],
"properties": {
"Node name for S&R": "PreviewImage"
},
"widgets_values": []
},
{
"id": 1,
"type": "Note",
"pos": [
-175.84976196289062,
102.76270294189453
],
"size": [
210,
88
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"If you would like to start with prompt"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 2,
"type": "Note",
"pos": [
-225.1866455078125,
624.7235107421875
],
"size": [
210,
88
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"If you would like to start with reference image + prompt"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 15,
"type": "PreviewImage",
"pos": [
719.5359497070312,
443.11285400390625
],
"size": [
140,
26
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 36
}
],
"outputs": [],
"properties": {
"Node name for S&R": "PreviewImage"
},
"widgets_values": []
},
{
"id": 17,
"type": "PreviewImage",
"pos": [
1132.783935546875,
517.3931884765625
],
"size": [
140,
26
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 44
}
],
"outputs": [],
"properties": {
"Node name for S&R": "PreviewImage"
},
"widgets_values": []
},
{
"id": 20,
"type": "GenerateStructuredPromptLiteNodeV2",
"pos": [
68.9760971069336,
82.11421966552734
],
"size": [
310.7749938964844,
174
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"name": "images",
"shape": 7,
"type": "IMAGE",
"link": null
}
],
"outputs": [
{
"name": "structured_prompt",
"type": "STRING",
"links": [
27
]
},
{
"name": "seed",
"type": "INT",
"links": [
28
]
}
],
"properties": {
"Node name for S&R": "GenerateStructuredPromptLiteNodeV2"
},
"widgets_values": [
"BRIA_API_TOKEN",
"",
"",
123456,
"randomize"
]
},
{
"id": 24,
"type": "GenerateImageLiteNodeV2",
"pos": [
460.6510314941406,
44.938873291015625
],
"size": [
270,
290
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "images",
"shape": 7,
"type": "IMAGE",
"link": null
},
{
"name": "structured_prompt",
"shape": 7,
"type": "STRING",
"widget": {
"name": "structured_prompt"
},
"link": 27
},
{
"name": "seed",
"shape": 7,
"type": "INT",
"widget": {
"name": "seed"
},
"link": 28
}
],
"outputs": [
{
"name": "image",
"type": "IMAGE",
"links": [
29
]
},
{
"name": "structured_prompt",
"type": "STRING",
"links": [
41
]
},
{
"name": "seed",
"type": "INT",
"links": [
42
]
}
],
"properties": {
"Node name for S&R": "GenerateImageLiteNodeV2"
},
"widgets_values": [
"BRIA_API_TOKEN",
"",
"FIBO",
"",
"1:1",
8,
5,
123456,
"randomize"
]
},
{
"id": 26,
"type": "RefineImageLiteNodeV2",
"pos": [
834.9641723632812,
46.47432327270508
],
"size": [
270,
290
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "structured_prompt",
"type": "STRING",
"widget": {
"name": "structured_prompt"
},
"link": 41
},
{
"name": "seed",
"shape": 7,
"type": "INT",
"widget": {
"name": "seed"
},
"link": 42
}
],
"outputs": [
{
"name": "image",
"type": "IMAGE",
"links": [
43
]
},
{
"name": "structured_prompt",
"type": "STRING",
"links": null
},
{
"name": "seed",
"type": "INT",
"links": null
}
],
"properties": {
"Node name for S&R": "RefineImageLiteNodeV2"
},
"widgets_values": [
"BRIA_API_TOKEN",
"",
"",
"FIBO",
"1:1",
8,
5,
123456,
"randomize"
]
},
{
"id": 25,
"type": "GenerateImageLiteNodeV2",
"pos": [
404.58843994140625,
532.5309448242188
],
"size": [
270,
290
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "images",
"shape": 7,
"type": "IMAGE",
"link": null
},
{
"name": "structured_prompt",
"shape": 7,
"type": "STRING",
"widget": {
"name": "structured_prompt"
},
"link": 34
},
{
"name": "seed",
"shape": 7,
"type": "INT",
"widget": {
"name": "seed"
},
"link": 35
}
],
"outputs": [
{
"name": "image",
"type": "IMAGE",
"links": [
36
]
},
{
"name": "structured_prompt",
"type": "STRING",
"links": [
45
]
},
{
"name": "seed",
"type": "INT",
"links": [
46
]
}
],
"properties": {
"Node name for S&R": "GenerateImageLiteNodeV2"
},
"widgets_values": [
"BRIA_API_TOKEN",
"",
"FIBO",
"",
"1:1",
8,
5,
123456,
"randomize"
]
},
{
"id": 27,
"type": "RefineImageLiteNodeV2",
"pos": [
820.26611328125,
558.9785766601562
],
"size": [
270,
290
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "structured_prompt",
"type": "STRING",
"widget": {
"name": "structured_prompt"
},
"link": 45
},
{
"name": "seed",
"shape": 7,
"type": "INT",
"widget": {
"name": "seed"
},
"link": 46
}
],
"outputs": [
{
"name": "image",
"type": "IMAGE",
"links": [
44
]
},
{
"name": "structured_prompt",
"type": "STRING",
"links": null
},
{
"name": "seed",
"type": "INT",
"links": null
}
],
"properties": {
"Node name for S&R": "RefineImageLiteNodeV2"
},
"widgets_values": [
"BRIA_API_TOKEN",
"",
"",
"FIBO",
"1:1",
8,
5,
123456,
"randomize"
]
},
{
"id": 21,
"type": "GenerateStructuredPromptLiteNodeV2",
"pos": [
3.162916421890259,
587.301025390625
],
"size": [
310.7749938964844,
174
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"name": "images",
"shape": 7,
"type": "IMAGE",
"link": null
}
],
"outputs": [
{
"name": "structured_prompt",
"type": "STRING",
"links": [
34
]
},
{
"name": "seed",
"type": "INT",
"links": [
35
]
}
],
"properties": {
"Node name for S&R": "GenerateStructuredPromptLiteNodeV2"
},
"widgets_values": [
"BRIA_API_TOKEN",
"",
"",
123456,
"randomize"
]
}
],
"links": [
[
27,
20,
0,
24,
1,
"STRING"
],
[
28,
20,
1,
24,
2,
"INT"
],
[
29,
24,
0,
6,
0,
"IMAGE"
],
[
34,
21,
0,
25,
1,
"STRING"
],
[
35,
21,
1,
25,
2,
"INT"
],
[
36,
25,
0,
15,
0,
"IMAGE"
],
[
41,
24,
1,
26,
0,
"STRING"
],
[
42,
24,
2,
26,
1,
"INT"
],
[
43,
26,
0,
5,
0,
"IMAGE"
],
[
44,
27,
0,
17,
0,
"IMAGE"
],
[
45,
25,
1,
27,
0,
"STRING"
],
[
46,
25,
2,
27,
1,
"INT"
]
],
"groups": [],
"config": {},
"extra": {
"ds": {
"scale": 0.6276708501927047,
"offset": [
650.5506889681789,
132.55696596915172
]
},
"frontendVersion": "1.25.11"
},
"version": 0.4
}
workflows/FIBO_Workflow.json → workflows/generate_image_fibo_workflow.json
+518 -365
View File
File diff suppressed because it is too large Load Diff