# Torch torch==2.6.0 torchvision==0.21.0 transformers==4.51.3 diffusers==0.33.1 accelerate==1.6.0 peft==0.15.2 safetensors==0.5.3 lightning==2.5.1.post0 # Image Processing opencv-python==4.11.0.86 pillow==11.2.1 # Data numpy==2.2.5 pandas==2.2.3 matplotlib==3.10.3 # HuggingFace datasets==3.5.1 tokenizers==0.21.1 huggingface-hub==0.30.2 sentencepiece==0.2.0 # Web Service fastapi==0.115.12 gradio==5.32.0 gradio-client==1.10.2 uvicorn==0.34.2 starlette==0.46.2 aiofiles==24.1.0 # Utils tqdm==4.67.1 click==8.1.8 typer==0.15.3 pydantic==2.11.3 jinja2==3.1.6 pyyaml==6.0.2 requests==2.32.3 einops==0.8.1 ruff==0.11.9
ComfyUI-PosterCraft is now available in ComfyUI, PosterCraft is a unified framework for high-quality aesthetic poster generation that excels in precise text rendering, seamless integration of abstract art, striking layouts, and stylistic harmony.
cd ComfyUI/custom_nodes
git clone https://github.com/Yuan-ManX/ComfyUI-PosterCraft.gitcd ComfyUI-PosterCraft
# Create conda environment
conda create -n postercraft python=3.11
conda activate postercraft
# Install dependencies
pip install -r requirements.txtWe provide the weights for our core models, fine-tuned at different stages of the PosterCraft pipeline.
| Model | Stage | Description | Download |
|---|---|---|---|
| 🎯 PosterCraft-v1_RL | Stage 3: Aesthetic-Text RL | Optimized via Aesthetic-Text Preference Optimization for higher-order aesthetic trade-offs. | 🤗 HF |
| 🔄 PosterCraft-v1_Reflect | Stage 4: Vision-Language Feedback | Iteratively refined using vision-language feedback for further harmony and content accuracy. | 🤗 HF |