thethreemagi/bookapp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

v1.2.0: Prefer Gemini 2.x models, improve cover generation and Docker health

Browse Source 
Model selection (ai.py):
- get_optimal_model() now scores Gemini 2.5 > 2.0 > 1.5 when ranking candidates
- get_default_models() fallbacks updated to gemini-2.0-pro-exp (logic) and gemini-2.0-flash (writer/artist)
- AI selection prompt rewritten: includes Gemini 2.x pricing context, guidance to avoid 'thinking' models for writer/artist roles, and instructions to prefer 2.x over 1.5
- Added image_model_name and image_model_source globals for UI visibility
- init_models() now reads MODEL_IMAGE_HINT; tries imagen-3.0-generate-001 then imagen-3.0-fast-generate-001 on both Gemini API and Vertex AI paths

Cover generation (marketing.py):
- Fixed display bug: "Attempt X/5" now correctly reads "Attempt X/3"
- Added imagen-3.0-fast-generate-001 as intermediate fallback before legacy Imagen 2
- Quality threshold: images with score < 5 are only kept if nothing better exists
- Smarter prompt refinement on retry: deformity, blur, and watermark critique keywords each append targeted corrections to the art prompt
- Fixed missing sys import (sys.platform check for macOS was silently broken)

Config / Docker:
- config.py: added MODEL_IMAGE_HINT env var, bumped version to 1.2.0
- docker-compose.yml: added MODEL_IMAGE environment variable
- Dockerfile: added libpng-dev and libfreetype6-dev for better font/PNG rendering; added HEALTHCHECK so Portainer detects unhealthy containers

System status UI:
- system_status.html: added Image row showing active Imagen model and provider (Gemini API / Vertex AI)
- Added cache expiry countdown with colour-coded badges

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Mike Wichers
2026-02-20 10:31:02 -05:00
parent 5e0def99c1
commit 2a9a605800
7 changed files with 171 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files

71
modules/marketing.py
View File

@@ -1,10 +1,10 @@
import os
import sys
import json
import shutil
import textwrap
import subprocess
import requests
import google.generativeai as genai
from . import utils
import config
from modules import ai
@@ -212,59 +212,82 @@ def generate_cover(bp, folder, tracking=None, feedback=None, interactive=False):
best_img_score = 0
best_img_path = None
MAX_IMG_ATTEMPTS = 3
if regenerate_image:
for i in range(1, 4):
utils.log("MARKETING", f"Generating cover art (Attempt {i}/5)...")
for i in range(1, MAX_IMG_ATTEMPTS + 1):
utils.log("MARKETING", f"Generating cover art (Attempt {i}/{MAX_IMG_ATTEMPTS})...")
try:
if not ai.model_image: raise ImportError("No Image Generation Model available.")
status = "success"
try:
result = ai.model_image.generate_images(prompt=art_prompt, number_of_images=1, aspect_ratio=ar)
except Exception as e:
if "resource" in str(e).lower() and ai.HAS_VERTEX:
utils.log("MARKETING", "⚠️ Imagen 3 failed. Trying Imagen 2...")
fb_model = ai.VertexImageModel.from_pretrained("imagegeneration@006")
result = fb_model.generate_images(prompt=art_prompt, number_of_images=1, aspect_ratio=ar)
status = "success_fallback"
else: raise e
err_lower = str(e).lower()
# Try fast imagen variant before falling back to legacy
if ai.HAS_VERTEX and ("resource" in err_lower or "quota" in err_lower):
try:
utils.log("MARKETING", "⚠️ Imagen 3 failed. Trying Imagen 3 Fast...")
fb_model = ai.VertexImageModel.from_pretrained("imagen-3.0-fast-generate-001")
result = fb_model.generate_images(prompt=art_prompt, number_of_images=1, aspect_ratio=ar)
status = "success_fast"
except Exception:
utils.log("MARKETING", "⚠️ Imagen 3 Fast failed. Trying Imagen 2...")
fb_model = ai.VertexImageModel.from_pretrained("imagegeneration@006")
result = fb_model.generate_images(prompt=art_prompt, number_of_images=1, aspect_ratio=ar)
status = "success_fallback"
else:
raise e
attempt_path = os.path.join(folder, f"cover_art_attempt_{i}.png")
result.images[0].save(attempt_path)
utils.log_usage(folder, "imagen", image_count=1)
score, critique = evaluate_image_quality(attempt_path, art_prompt, ai.model_writer, folder)
if score is None: score = 0
utils.log("MARKETING", f" -> Image Score: {score}/10. Critique: {critique}")
utils.log_image_attempt(folder, "cover", art_prompt, f"cover_art_{i}.png", status, score=score, critique=critique)
if interactive:
# Open image for review
try:
if os.name == 'nt': os.startfile(attempt_path)
elif sys.platform == 'darwin': subprocess.call(('open', attempt_path))
else: subprocess.call(('xdg-open', attempt_path))
except: pass
if Confirm.ask(f"Accept cover attempt {i} (Score: {score})?", default=True):
best_img_path = attempt_path
break
else:
utils.log("MARKETING", "User rejected cover. Retrying...")
continue
if score > best_img_score:
# Only keep as best if score meets minimum quality bar
if score >= 5 and score > best_img_score:
best_img_score = score
best_img_path = attempt_path
if score == 10:
utils.log("MARKETING", " -> Perfect image accepted.")
elif best_img_path is None and score > 0:
# Accept even low-quality image if we have nothing else
best_img_score = score
best_img_path = attempt_path
if score >= 9:
utils.log("MARKETING", " -> High quality image accepted.")
break
if "scar" in critique.lower() or "deform" in critique.lower() or "blur" in critique.lower():
art_prompt += " (Ensure high quality, clear skin, no scars, sharp focus)."
# Refine prompt based on critique keywords
prompt_additions = []
critique_lower = critique.lower() if critique else ""
if "scar" in critique_lower or "deform" in critique_lower:
prompt_additions.append("perfect anatomy, no deformities")
if "blur" in critique_lower or "blurry" in critique_lower:
prompt_additions.append("sharp focus, highly detailed")
if "text" in critique_lower or "letter" in critique_lower:
prompt_additions.append("no text, no letters, no watermarks")
if prompt_additions:
art_prompt += f". ({', '.join(prompt_additions)})"
except Exception as e:
utils.log("MARKETING", f"Image generation failed: {e}")
if "quota" in str(e).lower(): break