Blogger builds 35mm film scanning automation pipeline with Claude and Qwen3-VL
The author uses Claude, numpy negative conversion, LaMa inpainting model and Qwen3-VL in local Ollama to automate the manual scan-processing workflow of about 4 hours per 36-frame roll, and builds a film-style online gallery via Cloudflare R2.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original