comicbook / src /app /queries

Commit History

  1. fix

    Julian Bilcke
    9f66c7d
  2. fix

    Julian Bilcke
    3220193
  3. anchoring story chunks into the larger length

    Julian Bilcke
    ee1b7bf
  4. try to fix the nb of panels issue

    Julian Bilcke
    d303a22

  1. improve performance of the LLM

    Julian Bilcke
    26ef0a6
  2. add new "fast LLM" optimization

    Julian Bilcke
    9bfb451
  3. added suggestion from user + work on the progressive loader

    Julian Bilcke
    faf4ba4
  4. work on a new approach: generate small chunks of a story instead of big one

    Julian Bilcke
    9bcdb59

  1. let's use Zephyr 7b for storytelling

    Julian Bilcke
    9052a89

  1. add new turbo mode

    Julian Bilcke
    4f8f050

  1. fix openai glitch

    Julian Bilcke
    e22103d

  1. better captions

    Julian Bilcke
    f309083

  1. minor improvement

    Julian Bilcke
    4b2fc57
  2. fix the dual prompting system

    Julian Bilcke
    690ffd8
  3. change to the prompt

    Julian Bilcke
    cea3188

  1. let's use two pages

    Julian Bilcke
    5dd2af5

  1. seems to be in order

    Julian Bilcke
    c65c1bb
  2. planned maintenance

    Julian Bilcke
    855183b

  1. fixes for the Inference API

    Julian Bilcke
    81eb27e

  1. increase quality of VideoChain outputs

    Julian Bilcke
    1e641f1
  2. experimenting with things

    Julian Bilcke
    048071f
  3. the dynamic import is causing issue during build, but it's not an issue we can just put the var init inside the function

    Julian Bilcke
    6463491
  4. fix this error: https://nextjs.org/docs/messages/no-assign-module-variable

    Julian Bilcke
    9074714
  5. fix predict import error and change README

    e1c1857

  1. update env variables

    Julian Bilcke
    879455c
  2. fix merge

    Julian Bilcke
    274b152
  3. allow support for Inference API for SDXL

    Julian Bilcke
    e52146b
  4. support openai api

    me@idoubi.cc
    287a603

  1. Update src/app/queries/predict.ts

    a3bf1f1

  1. new version, able to support Inference API models

    Julian Bilcke
    3ca0269

  1. fixed upscaling

    Julian Bilcke
    f5d8038

  1. up

    Julian Bilcke
    c32ec0d

  1. handle a new hallucination case

    Julian Bilcke
    2531bbf

  1. adding some counter measures to reduce the pressure on the server

    Julian Bilcke
    cb3fdda
  2. various improvements

    Julian Bilcke
    974ed41

  1. try to improve robustness of LLM responses

    Julian Bilcke
    2f7798c
  2. bugfix, improve quality, add layou

    Julian Bilcke
    11443d4
  3. add LLM-generated story

    Julian Bilcke
    f4dea7d

  1. initial commit

    Julian Bilcke
    624088c