Alexander Garzon
6d3d2fca46
BYOK OpenAI gpt-image generation and editing nodes for ComfyUI — calls go directly to the OpenAI API with your own key (no proxy, no credit markup). - Two nodes: "Imagent: OpenAI Image" (text-to-image) and "Imagent: OpenAI Image Edit" (edit / inpaint / multi-reference compose). - Models gpt-image-2 / gpt-image-1.5 / gpt-image-1 with a per-model dynamic UI (comfy_api DynamicCombo): size, background, custom WxH, and input_fidelity are revealed only for the models that support them. - Edit node accepts an auto-growing set of reference images (up to 16) plus an optional inpaint mask; generate supports batches up to 8. - API key via OPENAI_API_KEY or a local config.json. Requires ComfyUI >= 0.23.0.
27 lines
824 B
YAML
27 lines
824 B
YAML
services:
|
|
comfyui:
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile
|
|
args:
|
|
# Override with `docker compose build --build-arg COMFYUI_REF=v0.3.27`
|
|
COMFYUI_REF: master
|
|
image: comfyui-imagent-dev:latest
|
|
container_name: comfyui-imagent-dev
|
|
ports:
|
|
- "8188:8188"
|
|
environment:
|
|
# Checked before config.json by imagent/client.py. Set OPENAI_API_KEY in
|
|
# your shell before `up`, or it passes through empty.
|
|
OPENAI_API_KEY: ${OPENAI_API_KEY:-}
|
|
volumes:
|
|
# The node under development: bind-mount the repo into custom_nodes so
|
|
# edits reload on container restart.
|
|
- ../:/opt/ComfyUI/custom_nodes/comfyui-imagent:rw
|
|
# Persistent ComfyUI user dir.
|
|
- comfyui_user:/opt/ComfyUI/user
|
|
restart: unless-stopped
|
|
|
|
volumes:
|
|
comfyui_user:
|