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

feat: Rebuild cover pipeline with full evaluate→critique→refine→retry quality gates

Browse Source 
Major changes to marketing/cover.py:
- Split evaluate_image_quality() into two purpose-built functions:
  * evaluate_cover_art(): 5-rubric scoring (visual impact, genre fit, composition,
    quality, clean image) with auto-fail for visible text (score capped at 4) and
    deductions for deformed anatomy
  * evaluate_cover_layout(): 5-rubric scoring (legibility, typography, placement,
    professional polish, genre signal) with auto-fail for illegible title (capped at 4)
- Added validate_art_prompt(): pre-validates the Imagen prompt before generation —
  strips accidental text instructions, ensures focal point + rule-of-thirds + genre fit
- Added _build_visual_context(): extracts protagonist/antagonist descriptions and key
  themes from tracking data into structured visual context for the art director prompt
- Score thresholds raised to match chapter pipeline: ART_PASSING=7, ART_AUTO_ACCEPT=8,
  LAYOUT_PASSING=7 (was: art>=5 or >0, layout breaks only at ==10)
- Critique-driven art prompt refinement between attempts: full LLM rewrite of the
  Imagen prompt using the evaluator's actionable feedback (not just keyword appending)
- Layout loop now breaks early at score>=7 (was: only at ==10, so never)
- Design prompt strengthened with explicit character/visual context and NO TEXT clause

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Mike Wichers
2026-02-22 22:24:27 -05:00
parent 4f2449f79b
commit 3a42d1a339
1 changed files with 469 additions and 280 deletions
Download Patch File Download Diff File Expand all files Collapse all files

749
marketing/cover.py
View File

@@ -14,27 +14,187 @@ try:
except ImportError:
HAS_PIL = False
# Score gates (mirrors chapter writing pipeline thresholds)
ART_SCORE_AUTO_ACCEPT = 8 # Stop retrying — image is excellent
ART_SCORE_PASSING = 7 # Acceptable; keep as best candidate
LAYOUT_SCORE_PASSING = 7 # Accept layout and stop retrying
def evaluate_image_quality(image_path, prompt, model, folder=None):
if not HAS_PIL: return None, "PIL not installed"
# ---------------------------------------------------------------------------
# Evaluation helpers
# ---------------------------------------------------------------------------
def evaluate_cover_art(image_path, genre, title, model, folder=None):
"""Score generated cover art against a professional book-cover rubric.
Returns (score: int | None, critique: str).
Auto-fail conditions:
- Any visible text/watermarks → score capped at 4
- Blurry or deformed anatomy → deduct 2 points
"""
if not HAS_PIL:
return None, "PIL not installed"
try:
img = Image.open(image_path)
response = model.generate_content([f"""
ROLE: Art Critic
TASK: Analyze generated image against prompt.
PROMPT: '{prompt}'
OUTPUT_FORMAT (JSON): {{ "score": int (1-10), "reason": "string" }}
""", img])
model_name = getattr(model, 'name', "logic-pro")
if folder: utils.log_usage(folder, model_name, response.usage_metadata)
data = json.loads(utils.clean_json(response.text))
return data.get('score'), data.get('reason')
except Exception as e: return None, str(e)
prompt = f"""
ROLE: Professional Book Cover Art Critic
TASK: Score this AI-generated cover art for a {genre} novel titled '{title}'.
SCORING RUBRIC (1-10):
1. VISUAL IMPACT: Is the image immediately arresting? Does it demand attention on a shelf?
2. GENRE FIT: Does the visual style, mood, and colour palette unmistakably signal {genre}?
3. COMPOSITION: Is there a clear focal point? Are the top or bottom thirds usable for title/author text overlay?
4. TECHNICAL QUALITY: Sharp, detailed, free of deformities, blurring, or AI artefacts?
5. CLEAN IMAGE: Absolutely NO text, letters, numbers, watermarks, logos, or UI elements?
SCORING SCALE:
- 9-10: Masterclass cover art, ready for a major publisher
- 7-8: Professional quality, genre-appropriate, minor flaws only
- 5-6: Usable but generic or has one significant flaw
- 1-4: Unusable — major artefacts, wrong genre, deformed figures, or visible text
AUTO-FAIL RULES (apply before scoring):
- If ANY text, letters, watermarks or UI elements are visible → score CANNOT exceed 4. State this explicitly.
- If figures have deformed anatomy or blurring → deduct 2 from your final score.
OUTPUT_FORMAT (JSON): {{"score": int, "critique": "Specific issues citing what to fix in the next attempt.", "actionable": "One concrete change to the image prompt that would improve the next attempt."}}
"""
response = model.generate_content([prompt, img])
model_name = getattr(model, 'name', "logic")
if folder:
utils.log_usage(folder, model_name, response.usage_metadata)
data = json.loads(utils.clean_json(response.text))
score = data.get('score')
critique = data.get('critique', '')
if data.get('actionable'):
critique += f" FIX: {data['actionable']}"
return score, critique
except Exception as e:
return None, str(e)
def evaluate_cover_layout(image_path, title, author, genre, font_name, model, folder=None):
"""Score the finished cover (art + text overlay) as a professional book cover.
Returns (score: int | None, critique: str).
"""
if not HAS_PIL:
return None, "PIL not installed"
try:
img = Image.open(image_path)
prompt = f"""
ROLE: Graphic Design Critic
TASK: Score this finished book cover for '{title}' by {author} ({genre}).
SCORING RUBRIC (1-10):
1. LEGIBILITY: Is the title instantly readable? High contrast against the background?
2. TYPOGRAPHY: Does the font '{font_name}' suit the {genre} genre? Is sizing proportional?
3. PLACEMENT: Is the title placed where it doesn't obscure the focal point? Is the author name readable?
4. PROFESSIONAL POLISH: Does this look like a published, commercially-viable cover?
5. GENRE SIGNAL: At a glance, does the whole cover (art + text) correctly signal {genre}?
SCORING SCALE:
- 9-10: Indistinguishable from a professional published cover
- 7-8: Strong cover, minor refinement would help
- 5-6: Passable but text placement or contrast needs work
- 1-4: Unusable — unreadable text, clashing colours, or amateurish layout
AUTO-FAIL: If the title text is illegible (low contrast, obscured, or missing) → score CANNOT exceed 4.
OUTPUT_FORMAT (JSON): {{"score": int, "critique": "Specific layout issues.", "actionable": "One change to position, colour, or font size that would fix the worst problem."}}
"""
response = model.generate_content([prompt, img])
model_name = getattr(model, 'name', "logic")
if folder:
utils.log_usage(folder, model_name, response.usage_metadata)
data = json.loads(utils.clean_json(response.text))
score = data.get('score')
critique = data.get('critique', '')
if data.get('actionable'):
critique += f" FIX: {data['actionable']}"
return score, critique
except Exception as e:
return None, str(e)
# ---------------------------------------------------------------------------
# Art prompt pre-validation
# ---------------------------------------------------------------------------
def validate_art_prompt(art_prompt, meta, model, folder=None):
"""Pre-validate and improve the image generation prompt before calling Imagen.
Checks for: accidental text instructions, vague focal point, missing composition
guidance, and genre mismatch. Returns improved prompt or original on failure.
"""
genre = meta.get('genre', 'Fiction')
title = meta.get('title', 'Untitled')
check_prompt = f"""
ROLE: Art Director
TASK: Review and improve this image generation prompt for a {genre} book cover titled '{title}'.
CURRENT_PROMPT:
{art_prompt}
CHECK FOR AND FIX:
1. Any instruction to render text, letters, or the title? → Remove it (text is overlaid separately).
2. Is there a specific, memorable FOCAL POINT described? → Add one if missing.
3. Does the colour palette and style match {genre} conventions? → Correct if off.
4. Is RULE OF THIRDS composition mentioned (space at top/bottom for title overlay)? → Add if missing.
5. Does it end with "No text, no letters, no watermarks"? → Ensure this is present.
Return the improved prompt under 200 words.
OUTPUT_FORMAT (JSON): {{"improved_prompt": "..."}}
"""
try:
resp = model.generate_content(check_prompt)
if folder:
utils.log_usage(folder, model.name, resp.usage_metadata)
data = json.loads(utils.clean_json(resp.text))
improved = data.get('improved_prompt', '').strip()
if improved and len(improved) > 50:
utils.log("MARKETING", " -> Art prompt validated and improved.")
return improved
except Exception as e:
utils.log("MARKETING", f" -> Art prompt validation failed: {e}. Using original.")
return art_prompt
# ---------------------------------------------------------------------------
# Visual context helper
# ---------------------------------------------------------------------------
def _build_visual_context(bp, tracking):
"""Extract structured visual context: protagonist, antagonist, key themes."""
lines = []
chars = bp.get('characters', [])
protagonist = next((c for c in chars if 'protagonist' in c.get('role', '').lower()), None)
if protagonist:
lines.append(f"PROTAGONIST: {protagonist.get('name')} — {protagonist.get('description', '')[:200]}")
antagonist = next((c for c in chars if 'antagonist' in c.get('role', '').lower()), None)
if antagonist:
lines.append(f"ANTAGONIST: {antagonist.get('name')} — {antagonist.get('description', '')[:150]}")
if tracking and tracking.get('characters'):
for name, data in list(tracking['characters'].items())[:2]:
desc = ', '.join(data.get('descriptors', []))[:120]
if desc:
lines.append(f"CHARACTER VISUAL ({name}): {desc}")
if tracking and tracking.get('events'):
recent = [e for e in tracking['events'][-3:] if isinstance(e, str)]
if recent:
lines.append(f"KEY THEMES/EVENTS: {'; '.join(recent)[:200]}")
return "\n".join(lines) if lines else ""
# ---------------------------------------------------------------------------
# Main entry point
# ---------------------------------------------------------------------------
def generate_cover(bp, folder, tracking=None, feedback=None, interactive=False):
if not HAS_PIL:
utils.log("MARKETING", "Pillow not installed. Skipping image cover.")
utils.log("MARKETING", "Pillow not installed. Skipping cover.")
return
utils.log("MARKETING", "Generating cover...")
@@ -45,13 +205,7 @@ def generate_cover(bp, folder, tracking=None, feedback=None, interactive=False):
if orientation == "Landscape": ar = "4:3"
elif orientation == "Square": ar = "1:1"
visual_context = ""
if tracking:
visual_context = "IMPORTANT VISUAL CONTEXT:\n"
if 'events' in tracking:
visual_context += f"Key Events/Themes: {json.dumps(tracking['events'][-5:])}\n"
if 'characters' in tracking:
visual_context += f"Character Appearances: {json.dumps(tracking['characters'])}\n"
visual_context = _build_visual_context(bp, tracking)
regenerate_image = True
design_instruction = ""
@@ -60,18 +214,15 @@ def generate_cover(bp, folder, tracking=None, feedback=None, interactive=False):
regenerate_image = False
if feedback and feedback.strip():
utils.log("MARKETING", f"Analyzing feedback: '{feedback}'...")
utils.log("MARKETING", f"Analysing feedback: '{feedback}'...")
analysis_prompt = f"""
ROLE: Design Assistant
TASK: Analyze user feedback on cover.
TASK: Analyse user feedback on a book cover.
FEEDBACK: "{feedback}"
DECISION:
1. Keep the current background image but change text/layout/color (REGENERATE_LAYOUT).
2. Create a completely new background image (REGENERATE_IMAGE).
OUTPUT_FORMAT (JSON): {{ "action": "REGENERATE_LAYOUT" or "REGENERATE_IMAGE", "instruction": "Specific instruction for Art Director" }}
1. Keep the background image; change only text/layout/colour → REGENERATE_LAYOUT
2. Create a completely new background image → REGENERATE_IMAGE
OUTPUT_FORMAT (JSON): {{"action": "REGENERATE_LAYOUT" or "REGENERATE_IMAGE", "instruction": "Specific instruction for the Art Director."}}
"""
try:
resp = ai_models.model_logic.generate_content(analysis_prompt)
@@ -79,24 +230,24 @@ def generate_cover(bp, folder, tracking=None, feedback=None, interactive=False):
decision = json.loads(utils.clean_json(resp.text))
if decision.get('action') == 'REGENERATE_LAYOUT':
regenerate_image = False
utils.log("MARKETING", "Feedback indicates keeping image. Regenerating layout only.")
utils.log("MARKETING", "Feedback: keeping image, regenerating layout only.")
design_instruction = decision.get('instruction', feedback)
except:
except Exception:
utils.log("MARKETING", "Feedback analysis failed. Defaulting to full regeneration.")
genre = meta.get('genre', 'Fiction')
tone = meta.get('style', {}).get('tone', 'Balanced')
genre_style_map = {
'thriller': 'dark, cinematic, high-contrast photography style',
'mystery': 'moody, atmospheric, noir-inspired painting',
'romance': 'warm, painterly, soft-focus illustration',
'fantasy': 'epic digital painting, rich colours, mythic scale',
'science fiction': 'sharp digital art, cool palette, futuristic',
'horror': 'unsettling, dark atmospheric painting, desaturated',
'historical fiction': 'classical oil painting style, period-accurate',
'young adult': 'vibrant illustrated style, bold colours',
'thriller': 'dark, cinematic, high-contrast photography style',
'mystery': 'moody, atmospheric, noir-inspired painting',
'romance': 'warm, painterly, soft-focus illustration',
'fantasy': 'epic digital painting, rich colours, mythic scale',
'science fiction': 'sharp digital art, cool palette, futuristic',
'horror': 'unsettling dark atmospheric painting, desaturated',
'historical fiction':'classical oil painting style, period-accurate',
'young adult': 'vibrant illustrated style, bold colours',
}
suggested_style = genre_style_map.get(genre.lower(), 'professional digital illustration or photography')
suggested_style = genre_style_map.get(genre.lower(), 'professional digital illustration')
design_prompt = f"""
ROLE: Art Director
@@ -108,258 +259,296 @@ def generate_cover(bp, folder, tracking=None, feedback=None, interactive=False):
- TONE: {tone}
- SUGGESTED_VISUAL_STYLE: {suggested_style}
VISUAL_CONTEXT (characters and key themes from the story):
{visual_context if visual_context else "Use genre conventions."}
VISUAL_CONTEXT (characters and themes from the finished story — use these):
{visual_context if visual_context else "Use strong genre conventions."}
USER_FEEDBACK: {feedback if feedback else "None"}
DESIGN_INSTRUCTION: {design_instruction if design_instruction else "Create a compelling, genre-appropriate cover."}
COVER_ART_RULES:
- The art_prompt must produce an image with NO text, no letters, no numbers, no watermarks, no UI elements, no logos.
- Describe a clear FOCAL POINT (e.g. the protagonist, a dramatic scene, a symbolic object).
- Use RULE OF THIRDS composition — leave visual space at top and/or bottom for the title and author text to be overlaid.
- Describe LIGHTING that reinforces the tone (e.g. "harsh neon backlight" for thriller, "golden hour" for romance).
- Describe the COLOUR PALETTE explicitly (e.g. "deep crimson and shadow-black", "soft rose gold and cream").
- Characters must match their descriptions from VISUAL_CONTEXT if present.
- The art_prompt MUST produce an image with ABSOLUTELY NO text, letters, numbers, watermarks, UI elements, or logos. Text is overlaid separately.
- Describe a specific, memorable FOCAL POINT (e.g. protagonist mid-action, a symbolic object, a dramatic landscape).
- Use RULE OF THIRDS composition — preserve visual space at top AND bottom for title/author text overlay.
- Describe LIGHTING that reinforces the tone (e.g. "harsh neon backlight", "golden hour", "cold winter dawn").
- Specify the COLOUR PALETTE explicitly (e.g. "deep crimson and shadow-black", "soft rose gold and ivory cream").
- If characters are described in VISUAL_CONTEXT, their appearance MUST match those descriptions exactly.
- End the art_prompt with: "No text, no letters, no watermarks, no UI elements. {suggested_style} quality, 8k detail."
OUTPUT_FORMAT (JSON only, no markdown):
OUTPUT_FORMAT (JSON only, no markdown wrapper):
{{
"font_name": "Name of a Google Font suited to the genre (e.g. Cinzel for fantasy, Oswald for thriller, Playfair Display for romance)",
"primary_color": "#HexCode (dominant background/cover colour)",
"font_name": "One Google Font suited to {genre} (e.g. Cinzel for fantasy, Oswald for thriller, Playfair Display for romance)",
"primary_color": "#HexCode",
"text_color": "#HexCode (high contrast against primary_color)",
"art_prompt": "Detailed {suggested_style} image generation prompt. Begin with the style. Describe composition, focal point, lighting, colour palette, and any characters. End with: No text, no letters, no watermarks, photorealistic/painted quality, 8k detail."
"art_prompt": "Detailed image generation prompt. Style → Focal point → Composition → Lighting → Colour palette → Characters (if any). End with the NO TEXT clause."
}}
"""
try:
response = ai_models.model_artist.generate_content(design_prompt)
utils.log_usage(folder, ai_models.model_artist.name, response.usage_metadata)
design = json.loads(utils.clean_json(response.text))
bg_color = design.get('primary_color', '#252570')
art_prompt = design.get('art_prompt', f"Cover art for {meta.get('title')}")
with open(os.path.join(folder, "cover_art_prompt.txt"), "w") as f:
f.write(art_prompt)
img = None
width, height = 600, 900
best_img_score = 0
best_img_path = None
MAX_IMG_ATTEMPTS = 3
if regenerate_image:
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_models.model_image: raise ImportError("No Image Generation Model available.")
status = "success"
try:
result = ai_models.model_image.generate_images(prompt=art_prompt, number_of_images=1, aspect_ratio=ar)
except Exception as e:
err_lower = str(e).lower()
if ai_models.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_models.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_models.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)
cover_eval_criteria = (
f"Book cover art for a {genre} novel titled '{meta.get('title')}'.\n\n"
f"Evaluate STRICTLY as a professional book cover on these criteria:\n"
f"1. VISUAL IMPACT: Is the image immediately arresting and compelling?\n"
f"2. GENRE FIT: Does the visual style, mood, and palette match {genre}?\n"
f"3. COMPOSITION: Is there a clear focal point? Are top/bottom areas usable for title/author text?\n"
f"4. QUALITY: Is the image sharp, detailed, and free of deformities or blurring?\n"
f"5. CLEAN IMAGE: Are there absolutely NO text, watermarks, letters, or UI artifacts?\n"
f"Score 1-10. Deduct 3 points if any text/watermarks are visible. "
f"Deduct 2 if the image is blurry or has deformed anatomy."
)
score, critique = evaluate_image_quality(attempt_path, cover_eval_criteria, ai_models.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:
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
from rich.prompt import Confirm
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 >= 5 and score > best_img_score:
best_img_score = score
best_img_path = attempt_path
elif best_img_path is None and score > 0:
best_img_score = score
best_img_path = attempt_path
if score >= 9:
utils.log("MARKETING", " -> High quality image accepted.")
break
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
if best_img_path and os.path.exists(best_img_path):
final_art_path = os.path.join(folder, "cover_art.png")
if best_img_path != final_art_path:
shutil.copy(best_img_path, final_art_path)
img = Image.open(final_art_path).resize((width, height)).convert("RGB")
else:
utils.log("MARKETING", "Falling back to solid color cover.")
img = Image.new('RGB', (width, height), color=bg_color)
utils.log_image_attempt(folder, "cover", art_prompt, "cover.png", "fallback_solid")
else:
final_art_path = os.path.join(folder, "cover_art.png")
if os.path.exists(final_art_path):
utils.log("MARKETING", "Using existing cover art (Layout update only).")
img = Image.open(final_art_path).resize((width, height)).convert("RGB")
else:
utils.log("MARKETING", "Existing art not found. Forcing regeneration.")
img = Image.new('RGB', (width, height), color=bg_color)
font_path = download_font(design.get('font_name') or 'Arial')
best_layout_score = 0
best_layout_path = None
base_layout_prompt = f"""
ROLE: Graphic Designer
TASK: Determine text layout coordinates for a 600x900 cover.
METADATA:
- TITLE: {meta.get('title')}
- AUTHOR: {meta.get('author')}
- GENRE: {meta.get('genre')}
CONSTRAINT: Do NOT place text over faces.
OUTPUT_FORMAT (JSON):
{{
"title": {{ "x": Int, "y": Int, "font_size": Int, "font_name": "String", "color": "#Hex" }},
"author": {{ "x": Int, "y": Int, "font_size": Int, "font_name": "String", "color": "#Hex" }}
}}
"""
if feedback:
base_layout_prompt += f"\nUSER FEEDBACK: {feedback}\nAdjust layout/colors accordingly."
layout_prompt = base_layout_prompt
for attempt in range(1, 6):
utils.log("MARKETING", f"Designing text layout (Attempt {attempt}/5)...")
try:
response = ai_models.model_writer.generate_content([layout_prompt, img])
utils.log_usage(folder, ai_models.model_writer.name, response.usage_metadata)
layout = json.loads(utils.clean_json(response.text))
if isinstance(layout, list): layout = layout[0] if layout else {}
except Exception as e:
utils.log("MARKETING", f"Layout generation failed: {e}")
continue
img_copy = img.copy()
draw = ImageDraw.Draw(img_copy)
def draw_element(key, text_override=None):
elem = layout.get(key)
if not elem: return
if isinstance(elem, list): elem = elem[0] if elem else {}
text = text_override if text_override else elem.get('text')
if not text: return
f_name = elem.get('font_name') or 'Arial'
f_path = download_font(f_name)
try:
if f_path: font = ImageFont.truetype(f_path, elem.get('font_size', 40))
else: raise IOError("Font not found")
except: font = ImageFont.load_default()
x, y = elem.get('x', 300), elem.get('y', 450)
color = elem.get('color') or '#FFFFFF'
avg_char_w = font.getlength("A")
wrap_w = int(550 / avg_char_w) if avg_char_w > 0 else 20
lines = textwrap.wrap(text, width=wrap_w)
line_heights = []
for l in lines:
bbox = draw.textbbox((0, 0), l, font=font)
line_heights.append(bbox[3] - bbox[1] + 10)
total_h = sum(line_heights)
current_y = y - (total_h // 2)
for idx, line in enumerate(lines):
bbox = draw.textbbox((0, 0), line, font=font)
lx = x - ((bbox[2] - bbox[0]) / 2)
draw.text((lx, current_y), line, font=font, fill=color)
current_y += line_heights[idx]
draw_element('title', meta.get('title'))
draw_element('author', meta.get('author'))
attempt_path = os.path.join(folder, f"cover_layout_attempt_{attempt}.png")
img_copy.save(attempt_path)
eval_prompt = f"""
Analyze the text layout for the book title '{meta.get('title')}'.
CHECKLIST:
1. Is the text legible against the background?
2. Is the contrast sufficient?
3. Does it look professional?
"""
score, critique = evaluate_image_quality(attempt_path, eval_prompt, ai_models.model_writer, folder)
if score is None: score = 0
utils.log("MARKETING", f" -> Layout Score: {score}/10. Critique: {critique}")
if score > best_layout_score:
best_layout_score = score
best_layout_path = attempt_path
if score == 10:
utils.log("MARKETING", " -> Perfect layout accepted.")
break
layout_prompt = base_layout_prompt + f"\nCRITIQUE OF PREVIOUS ATTEMPT: {critique}\nAdjust position/color to fix this."
if best_layout_path:
shutil.copy(best_layout_path, os.path.join(folder, "cover.png"))
except Exception as e:
utils.log("MARKETING", f"Cover generation failed: {e}")
utils.log("MARKETING", f"Cover design failed: {e}")
return
bg_color = design.get('primary_color', '#252570')
art_prompt = design.get('art_prompt', f"Cover art for {meta.get('title')}")
font_name = design.get('font_name') or 'Playfair Display'
# Pre-validate and improve the art prompt before handing to Imagen
art_prompt = validate_art_prompt(art_prompt, meta, ai_models.model_logic, folder)
with open(os.path.join(folder, "cover_art_prompt.txt"), "w") as f:
f.write(art_prompt)
img = None
width, height = 600, 900
# -----------------------------------------------------------------------
# Phase 1: Art generation loop (evaluate → critique → refine → retry)
# -----------------------------------------------------------------------
best_art_score = 0
best_art_path = None
current_art_prompt = art_prompt
MAX_ART_ATTEMPTS = 3
if regenerate_image:
for attempt in range(1, MAX_ART_ATTEMPTS + 1):
utils.log("MARKETING", f"Generating cover art (Attempt {attempt}/{MAX_ART_ATTEMPTS})...")
attempt_path = os.path.join(folder, f"cover_art_attempt_{attempt}.png")
gen_status = "success"
try:
if not ai_models.model_image:
raise ImportError("No image generation model available.")
try:
result = ai_models.model_image.generate_images(
prompt=current_art_prompt, number_of_images=1, aspect_ratio=ar)
except Exception as img_err:
err_lower = str(img_err).lower()
if ai_models.HAS_VERTEX and ("resource" in err_lower or "quota" in err_lower):
try:
utils.log("MARKETING", "⚠️ Imagen 3 failed. Trying Imagen 3 Fast...")
fb = ai_models.VertexImageModel.from_pretrained("imagen-3.0-fast-generate-001")
result = fb.generate_images(prompt=current_art_prompt, number_of_images=1, aspect_ratio=ar)
gen_status = "success_fast"
except Exception:
utils.log("MARKETING", "⚠️ Imagen 3 Fast failed. Trying Imagen 2...")
fb = ai_models.VertexImageModel.from_pretrained("imagegeneration@006")
result = fb.generate_images(prompt=current_art_prompt, number_of_images=1, aspect_ratio=ar)
gen_status = "success_fallback"
else:
raise img_err
result.images[0].save(attempt_path)
utils.log_usage(folder, "imagen", image_count=1)
score, critique = evaluate_cover_art(
attempt_path, genre, meta.get('title', ''), ai_models.model_logic, folder)
if score is None:
score = 0
utils.log("MARKETING", f" -> Art Score: {score}/10. Critique: {critique}")
utils.log_image_attempt(folder, "cover", current_art_prompt,
f"cover_art_attempt_{attempt}.png", gen_status,
score=score, critique=critique)
if interactive:
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 Exception:
pass
from rich.prompt import Confirm
if Confirm.ask(f"Accept cover art attempt {attempt} (score {score})?", default=True):
best_art_path = attempt_path
best_art_score = score
break
else:
utils.log("MARKETING", "User rejected art. Regenerating...")
continue
# Track best image — prefer passing threshold; keep first usable as fallback
if score >= ART_SCORE_PASSING and score > best_art_score:
best_art_score = score
best_art_path = attempt_path
elif best_art_path is None and score > 0:
best_art_score = score
best_art_path = attempt_path
if score >= ART_SCORE_AUTO_ACCEPT:
utils.log("MARKETING", " -> High-quality art accepted early.")
break
# Critique-driven prompt refinement for next attempt
if attempt < MAX_ART_ATTEMPTS and critique:
refine_req = f"""
ROLE: Art Director
TASK: Rewrite the image prompt to fix the critique below. Keep under 200 words.
CRITIQUE: {critique}
ORIGINAL_PROMPT: {current_art_prompt}
RULES:
- Preserve genre style, focal point, and colour palette unless explicitly criticised.
- If text/watermarks were visible: reinforce "absolutely no text, no letters, no watermarks."
- If anatomy was deformed: add "perfect anatomy, professional figure illustration."
- If blurry: add "tack-sharp focus, highly detailed."
OUTPUT_FORMAT (JSON): {{"improved_prompt": "..."}}
"""
try:
rr = ai_models.model_logic.generate_content(refine_req)
utils.log_usage(folder, ai_models.model_logic.name, rr.usage_metadata)
rd = json.loads(utils.clean_json(rr.text))
improved = rd.get('improved_prompt', '').strip()
if improved and len(improved) > 50:
current_art_prompt = improved
utils.log("MARKETING", " -> Art prompt refined for next attempt.")
except Exception:
pass
except Exception as e:
utils.log("MARKETING", f"Image generation attempt {attempt} failed: {e}")
if "quota" in str(e).lower():
break
if best_art_path and os.path.exists(best_art_path):
final_art_path = os.path.join(folder, "cover_art.png")
if best_art_path != final_art_path:
shutil.copy(best_art_path, final_art_path)
img = Image.open(final_art_path).resize((width, height)).convert("RGB")
utils.log("MARKETING", f" -> Best art: {best_art_score}/10.")
else:
utils.log("MARKETING", "⚠️ No usable art generated. Falling back to solid colour cover.")
img = Image.new('RGB', (width, height), color=bg_color)
utils.log_image_attempt(folder, "cover", art_prompt, "cover.png", "fallback_solid")
else:
final_art_path = os.path.join(folder, "cover_art.png")
if os.path.exists(final_art_path):
utils.log("MARKETING", "Using existing cover art (layout update only).")
img = Image.open(final_art_path).resize((width, height)).convert("RGB")
else:
utils.log("MARKETING", "Existing art not found. Using solid colour fallback.")
img = Image.new('RGB', (width, height), color=bg_color)
if img is None:
utils.log("MARKETING", "Cover generation aborted — no image available.")
return
font_path = download_font(font_name)
# -----------------------------------------------------------------------
# Phase 2: Text layout loop (evaluate → critique → adjust → retry)
# -----------------------------------------------------------------------
best_layout_score = 0
best_layout_path = None
base_layout_prompt = f"""
ROLE: Graphic Designer
TASK: Determine precise text layout coordinates for a 600×900 book cover image.
BOOK:
- TITLE: {meta.get('title')}
- AUTHOR: {meta.get('author', 'Unknown')}
- GENRE: {genre}
- FONT: {font_name}
- TEXT_COLOR: {design.get('text_color', '#FFFFFF')}
PLACEMENT RULES:
- Title in top third OR bottom third (not centre — that obscures the focal art).
- Author name in the opposite zone, or just below the title.
- Font sizes: title ~60-80px, author ~28-36px for a 600px-wide canvas.
- Do NOT place text over faces or the primary focal point.
- Coordinates are the CENTER of the text block (x=300 is horizontal centre).
{f"USER FEEDBACK: {feedback}. Adjust placement/colour accordingly." if feedback else ""}
OUTPUT_FORMAT (JSON):
{{
"title": {{"x": Int, "y": Int, "font_size": Int, "font_name": "{font_name}", "color": "#Hex"}},
"author": {{"x": Int, "y": Int, "font_size": Int, "font_name": "{font_name}", "color": "#Hex"}}
}}
"""
layout_prompt = base_layout_prompt
MAX_LAYOUT_ATTEMPTS = 5
for attempt in range(1, MAX_LAYOUT_ATTEMPTS + 1):
utils.log("MARKETING", f"Designing text layout (Attempt {attempt}/{MAX_LAYOUT_ATTEMPTS})...")
try:
resp = ai_models.model_writer.generate_content([layout_prompt, img])
utils.log_usage(folder, ai_models.model_writer.name, resp.usage_metadata)
layout = json.loads(utils.clean_json(resp.text))
if isinstance(layout, list):
layout = layout[0] if layout else {}
except Exception as e:
utils.log("MARKETING", f"Layout generation failed: {e}")
continue
img_copy = img.copy()
draw = ImageDraw.Draw(img_copy)
def draw_element(key, text_override=None):
elem = layout.get(key)
if not elem:
return
if isinstance(elem, list):
elem = elem[0] if elem else {}
text = text_override if text_override else elem.get('text')
if not text:
return
f_name = elem.get('font_name') or font_name
f_p = download_font(f_name)
try:
fnt = ImageFont.truetype(f_p, elem.get('font_size', 40)) if f_p else ImageFont.load_default()
except Exception:
fnt = ImageFont.load_default()
x, y = elem.get('x', 300), elem.get('y', 450)
color = elem.get('color') or design.get('text_color', '#FFFFFF')
avg_w = fnt.getlength("A")
wrap_w = int(550 / avg_w) if avg_w > 0 else 20
lines = textwrap.wrap(text, width=wrap_w)
line_heights = []
for ln in lines:
bbox = draw.textbbox((0, 0), ln, font=fnt)
line_heights.append(bbox[3] - bbox[1] + 10)
total_h = sum(line_heights)
current_y = y - (total_h // 2)
for idx, ln in enumerate(lines):
bbox = draw.textbbox((0, 0), ln, font=fnt)
lx = x - ((bbox[2] - bbox[0]) / 2)
draw.text((lx, current_y), ln, font=fnt, fill=color)
current_y += line_heights[idx]
draw_element('title', meta.get('title'))
draw_element('author', meta.get('author'))
attempt_path = os.path.join(folder, f"cover_layout_attempt_{attempt}.png")
img_copy.save(attempt_path)
score, critique = evaluate_cover_layout(
attempt_path, meta.get('title', ''), meta.get('author', ''), genre, font_name,
ai_models.model_writer, folder
)
if score is None:
score = 0
utils.log("MARKETING", f" -> Layout Score: {score}/10. Critique: {critique}")
if score > best_layout_score:
best_layout_score = score
best_layout_path = attempt_path
if score >= LAYOUT_SCORE_PASSING:
utils.log("MARKETING", f" -> Layout accepted (score {score} ≥ {LAYOUT_SCORE_PASSING}).")
break
if attempt < MAX_LAYOUT_ATTEMPTS:
layout_prompt = (base_layout_prompt
+ f"\n\nCRITIQUE OF ATTEMPT {attempt}: {critique}\n"
+ "Adjust coordinates, font_size, or color to fix these issues exactly.")
if best_layout_path:
shutil.copy(best_layout_path, os.path.join(folder, "cover.png"))
utils.log("MARKETING", f"Cover saved. Best layout score: {best_layout_score}/10.")
else:
utils.log("MARKETING", "⚠️ No layout produced. Cover not saved.")