search

heshengtao / comfyui_LLM_party

Dify in ComfyUI includes Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai/gemini interfaces, such as o1,ollama, qwen, GLM, deepseek, moonshot,doubao. Adapted to local llms, vlm, gguf such as llama-3.2, Linkage neo4j KG, graphRAG / RAG / html 2 img
GNU Affero General Public License v3.0
913 stars 89 forks source link

At most 1 image(s) may be provided in one request. #99

Open qy8502 opened 2 weeks ago

qy8502 commented 2 weeks ago

When an image is input into the API LLM node and queued twice, an error ‘At most 1 image(s) may be provided in one request.’ will occur. Using the qwen2-vl model, queuing multiple times will accumulate images.

heshengtao commented 2 weeks ago

I used the qwen-vl-max-0809 model and failed to reproduce your problem. It may just be your network interface card. If you submit a picture once and don't return any message, if you submit it again, it is likely that you have entered two pictures.