Do we need to have a class on book covers in WCP? There are a couple ways to do it and I'm sure I'm not doing it the best way yet, but I'm glad to share what i know in a Q&A format. I just need to know a good day/time for the most folks to participate and we'll record it for the rest. I'm getting pretty good results from the ones I show you all with very little effort. I'm working on a way to give more/easier control over type by using layers, and image under the type. These are really low effort below. They all could use some touchups.

I just thought I would share my experiences using local models with WordCrafter Pro. First a bit of my setup I run a Mac Studio M4 with 128GB RAM. So overkill for most things but large enough to run some larger size LLMs. With WordCrafter Pro I originally tried Ollama. I was able to see my local models without a problem however if I tried to connect with any of them, even setting context length, I kept getting 504 errors (if I remember correctly). So I moved over to LM Studio and tried with Gemma 4 31B with 128K context window. Again I could see my models but in case I could actually connect. I started with BrainStorm and threw it a silly throw away idea. Working through the BrainStorm process it was able to take this more or less random prompt and help craft it into something actual workable. I was able to take this and go through Story Dev then Character Creator. It seemed to more or less keep the conversation coherent and not drift too much from what we worked out. I did cause some direction changes, but much less than I normally would when working through a project, and it seemed to handle these changes fine. In this case I simply wanted evidence that it could work with the model then a finished project I would work on. Finally, I had it create the first chapter. The prose was more or less the standard AI generated I would expect but it generally kept to the story I wanted to create. In the process I did have a few cases where the prompt would process up to 100% on my side within LM Studio (i.e. finished) but then get disconnected and nothing showed up within WordCrafter Pro. Some of these might be some of the errors @Michael Culp was mentioning about in his post. Not sure who was at fault. However, asking it to 'continue' within the application seemed to work and allow it to finish the process as expected. Though I was starting to get the impression that the more context included within a prompt to the local model, the more likely it would run into problems and/or not be able to process at all.

Yes it can be done. Instead of deleting a single video in a youtube playlist I deleted the entire playlist. All 3600+ videos I had squirreled for a rainy day. Research, ideas, a couple of years worth of unsorted. Gone. Poof! The only way to somewhat "recover" is to scroll back through my history, but most of those I just saved for later and do not have an inkling what they were. So i'm in emotional and mental upheaval right now trying to take the high road and think, well if i don't know what they were I can't miss them right? Nope Nope Nope. My data pits: Youtube, Recall, Notes, Notion, Raindrop, etc.. are my first searches for things I know I know but cannot remember. Lesson in loss here I suppose. Or.....a notebooklm style rag database of all of my data pits to find.... nope nope nope. not going there either. time for a cry and then get back to life again

I was looking at the Error logs for WordCrafter.Pro this morning and I'm seeing some trends in the last several days. If you are having issues with errors let me know. I built this back side log so I can be a little proactive when folks are having issues but not saying anything. Sometimes it's the program, sometimes it's the ai model and the provider. And yes sometimes it's the guy sitting behind the coding console listening to his buddies Claude or Gemini gas lighting him. "I can't fix it if I don't know it's broke" was a sign in an early shop I worked in and I've never forgotten it. I don't have an easy way to pull how much $$ you have left on an api key but I can try to make the error messages you see make more sense. Something like "Hey add more $$ to your openai key" I renew the list of models about once a week to cover anything new from our providers and I have a couple of tests I run to see if they work in WCP before you see them. The failures get deactivated but some of them slip through (sigh..more work developing better testing). NONE of the gpt5 models passed this morning. Not sure what has changed on their side or this one so I will do more testing. Most notably I'm seeing failures in the reasoning and higher end models mostly. Fable, gpt 5.6 dol, luna and weirdly gpt-4o-mini. They are blowing the context window for the OUTPUT call. So the reasoning it is doing is taking a huge amount of tokens and not giving a full answer which makes me wonder if this is by design to make openai more money costing us for the reasoning to get better answers but not really. I'm thinking also that the increased guard rails on the system prompts that these models use before we send our prompts through are stealing some of our context windows. The system prompt for Anthropic's Claude Fable 5 is approximately 120,000 characters long (roughly 30,000 tokens consumed before the user types a single word). This is why they have started caching repeated prompts not to save us money, but to save face when they have to put stronger rules in place that takes up what we have to use.

What's Selling Right Now (And What to Have Ready Before the Holidays) Marketing Monday | DragonWorks Publishing We're in August. That makes this the most important marketing strategy window of the year. Not because August is a big sales month. It isn't. But what you do right now, the content you create, the book you finish, the ads you build, the back matter you fix, determines how much money you make between October and January. The authors who treat August as a slow month and coast through it will spend December watching other authors' launches while their own books sit quiet. Here's what the data says about what's selling, what's slowing, what's coming, and what you need to have ready. What's Selling Right Now Romance is still the undisputed market leader. This is not a trend. This is structural. Romance generates over $1.5 billion in annual sales and accounts for roughly one in five adult fiction books sold in the US. Indie authors dominate the Kindle Unlimited top spots in romance, and the genre's reader base, characterized by readers consuming five or more books per month, creates consistent demand that doesn't require viral moments to sustain. The specific corner of romance generating the most energy in 2026 is dark romance and romantasy. Adult fiction driven by the romantasy subgenre saw a 12.6% sales surge this year. Special edition hardcovers with sprayed edges are moving significant volume at $15 to $25 price points, which matters for authors thinking about premium print runs or Kickstarter campaigns. Romantasy is the fastest-climbing category. Thanks to social media virality and high-profile adaptations, fantasy titles with romance at the core are surging into bestseller territory faster than almost any other category. If you're writing in this space, your timing is good. If you're not, it's worth understanding what romantasy readers are responding to because those emotional expectations (high stakes, slow-burn romantic tension, strong world-building) are bleeding into adjacent categories.