When training lora model using train_text_to_image_lora.py, it reports errors like
UNet2DConditionModel object has no attribute attn_processors. Did you mean: set_attn_processor
After investigate reported error line in diffusers/loaders.py, and compare it with diffusers (version used) source code. Finally it is found that it is caused by diffusers package version. Uninstall the diffusers and re-install a lower version, problem fixed.
Most errors found in stable diffusion usage, which is caused by version mismatch. If you find diffusers or transformers related errors, first step is to check package version.
FEATURED TAGS
AI
Fintech
OpenAI
Generative AI
LLM
Investment
Artificial Intelligence
Startups
AI Agents
AI Safety
AI Governance
Anthropic
Agentic AI
Enterprise AI
Singapore
AI Infrastructure
Open Source AI
AI Research
Quantum Computing
AI Security
Venture Capital
Cybersecurity
Tokenization
China AI
AI Regulation
Stablecoins
Digital Payments
Agentic
Compliance
Payments
Regulation
RWA
AI Policy
US AI
Economy
Banking