Repository navigation
0.11.0: Estrai col pulsante e rilevatore piccolo, una cosa alla volta in VRAM, token/s, megapixel ovunque, LoRA attivi in Crea - #15
Merged
Conversation
…alla volta in VRAM, token al secondo, megapixel ovunque, LoRA attivi in Crea Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01K9poJitXQ1x3ZDHxioN2Cf
cammo22
marked this pull request as ready for review
October 15, 2026 15:50
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Cosa cambia
DaProdTrova, modellotrova-florence~460 MB scaricato al primo uso) al posto del Qwen3-VL per trovare i riquadri; opzione in Opzioni per tornare al Qwen3-VL e ripiego automatico se il rilevatore fallisce. I riquadri si leggono dai gettoni<loc_N>(provato il parser in Python). Il motore passa alla versione 6 (nuovo nodo).unaCosaAllaVolta, acceso di serie): passando da modello immagine a LLM/rilevatore (e viceversa)/free+ attesa chetorch_vram_totalscenda, prima di far partire il lavoro dopo.progressper token del TextGenerate) e nella riga dell'ultimo risultato.Verifica
npm run typecheckenpm run buildpassano; interfaccia provata connode test/interfaccia.mjs(la ricerca non parte da sola, parte col pulsante conmodalita: 'trova'), screenshot di Crea (LoRA, megapixel) e della barra con i tok/s.🤖 Generated with Claude Code
https://claude.ai/code/session_01K9poJitXQ1x3ZDHxioN2Cf
Generated by Claude Code