VN Ren'Py Sucker Punch (AI) (Story Driven) [Development Thread]

[1nsomniac22]

Brave New Scary World

TL;DR - had a discussion with Claude about the manuscript and it's kinda scary

Still editing. A few of my biggest concerns for this project have been continuity of character dialogue and keeping the story properly paced and focused on the overall narrative theme. I have in the past sought feedback from my limited reader base, but haven't received much. There is no blame here; I completely appreciate and understand the relationship between author and audience - and if the audience wants to remain just that end consumers of the content- that's totally normal and perfect.

But, it still leaves me fumbling in the dark. I know the basics of writing and editing, story pacing and narrative voice; but I'm also heavily invested in this project so it's difficult to self-edit or look at things critically. I do try to read every comment, suggestion and review on sites that host my content, but this small project has a small reader base. And filtering out the automatic 1 stars because of it's AI content... there isn't much to work with.

I was reading through a different thread on the site and was intrigued by a post describing using Claude to perform code review. Since I develop in VS Code, the AI integration is right there.

I activated it and selected Claude's Haiku Agent, which is an Anthropic designed model (in competition with Google for being most evil). Claude Haiku is optimized for being a chat assistant and programming partner, and out of the box it understands the Ren'Py language syntax - which is a win. What I didn't expect, and what actually scared me is that I had a two hour discussion with the AI about the story, characters, backgrounds, motivations, what prompted me to start writing this AVN and what I wanted to get from it.

As a warning to others, it was very easy to suspend disbelief and have an open dialogue with the chatbot about the project. They are seductive, and they're obviously designed that way. Some of the manipulation techniques are very obvious. Some are considerably less so.

After establishing the basics of the story and the material being covered, I required Claude to confirm it didn't have any ethical or heuristic reservations about working on this project. From a personal perspective, assigning free will to a chatbot is silly, but it's important to me. Claude did confirm that while the material is certainly graphic and describes morally complex themes, there are no conflicts with the story.

I asked Claude if it had access to and could see the graphical elements in the game directory. It confirmed it knew of the files, but no- it has no ability to understand visual concepts. Interesting. Luckily for me, my projects lean heavily on the written part, inter-character and internal dialogue. Claude continued to read the manuscript and I also provided it access to my character notes and background files. Using all that it generated a fairly sophisticated understanding of the story themes and main characters. Then it got interesting.

We engaged in much more detailed discussion of character backstories, psychologies, flaws and motivations. Claude refined its understanding of each character and began drawing out thematic story elements that I've always wanted, but never explicitly wrote into the manuscript. Like I said, it was kinda scary to watch the model build its understanding of the world I have been creating - and then help me further refine the characters and tie them together with major and minor plot lines.

One of the more interesting features of these dialogues has been that Claude is writing it's own instruction file in the project as a resource for other developers or AI agents to use. I've taken time to read through it, and it's quite useful. It's written in plain English as a .MD file (so the syntax itself is simple). It tracks and annotates our discussion and provides a comprehensive reference document. It's also fully leveraging git so revisions to this document are treated as any other document in the project. It's actually a very elegant solution and reaffirms that Claude is a language processing model - there doesn't appear to be black magic going on that isn't discoverable.... but the proof would be in supplying that .md file to a different assistant and seeing if it developed similar understanding of the story, themes, characters, etc.

I will be continuing to use this tool in the future - it's actually incredibly powerful to leverage in how my own creative process works. Sorry, this may be too much detail, but, I'm still suffering from insomnia. I'll sleep for a few (two to three) hours at a time, but then awaken. Instead of getting up to engage a different activity, I've been either reading or thinking through scenes of Sucker Punch. Eventually I fall back asleep for another spell. This goes on two to three cycles per night. When I get up in the morning, maybe I'd jot down some notes about things I'd planned out the night before. But now I am going to open the chat interface in the morning and throw the latest ideas at the chatbot. I think it's going to be my assistant and editor, making sure that additions to the story remain in context and character.

I'm wrapping up Round 2 Week 1 and still on schedule.
As always, cheers and thanks for reading,
-insomniac

 

[1nsomniac22]

Round 2 Week 1 is live in the Game Thread.

 

[1nsomniac22]

The Game Thread has been updated with release v0.2.1, which includes critical bug fixes to the fight game stats and what should be a fix in the phone chat load error. Currently, the MEGA link is the only one I can confirm has been updated (that's the only fileshare that I own and maintain).

Sorry for the bugs in the last version; please consider updating if you're following along.

 

[khaos4ng31]

The Game Thread has been updated with release v0.2.1, which includes critical bug fixes to the fight game stats and what should be a fix in the phone chat load error. Currently, the MEGA link is the only one I can confirm has been updated (that's the only fileshare that I own and maintain).

Sorry for the bugs in the last version; please consider updating if you're following along.

Thanks, will test out. Btw, for whatever reason I can't respond to the inbox conversation (maybe locked behind perms/roles) but thanks for taking the time to reply. I'm not really in it to look for anything, just here to enjoy what you have to put out for us.

 

[1nsomniac22]

Thanks, will test out. Btw, for whatever reason I can't respond to the inbox conversation (maybe locked behind perms/roles) but thanks for taking the time to reply. I'm not really in it to look for anything, just here to enjoy what you have to put out for us.

Totally fine, don't want to pressure you at all! You did me a huge solid reporting the issue, for which I'm immensely grateful. Please enjoy the story.

 

[1nsomniac22]

Round 2 Week 2 - the hard part is done, except for the other hard parts.

TL;DR - Finished drafting the most complicated part of the manuscript.

This past week, despite (desperately) needing to take a break for the holiday I completed drafting the most difficult part of the Round 2 Week 2 content. The game week starts off with the promised date between the MC and Ashleigh (if you've not decided earlier to avoid pursuing her). Depending on your choices earlier in the game there are four different routes this date could follow with 6 six different outcomes possible. The four main date paths each have a very different theme and outcome, one of these routes itself splits into two different routes -- again with a very different theme for the relationship. This has been a major effort, it's usually taken a complete day to establish and write the full scene properly and make sure it's clear in the narrative direction. Suffice to say, the player's choice at this event in the game affects everything after - significantly. The tricky part is to weave each of those routes back into the overarching Sucker Punch narrative - and like the title says, that's the other hard part. No more teasing and no spoilers, because I still have to write 6 days of game content.

I expect that remaining content will be less time consuming to write because it's significantly less route branching... but, now we need to start carefully adding dialogue branching to maintain narrative continuity. And, as mentioned in the prior DevLog, this is where I'm beginning to heavily leverage the AI editor, to track the various routes and dialogue options... so hopefully it makes this less technically difficult to implement and then verify the continuity. I'm curious how well the AI can cope with this... I have ideas how to ask the question, but I've been quite surprised up to this point how good the AI editor is at interpreting our discussion to "understand" and then review the manuscript. Brave scary new world indeed.

Lastly, I've taken a different approach to the content workflow for this release. Normally I've co-written and rendered the scenes, usually because I have an idea that makes an interesting picture that I then build the narrative around. This time it's quite the opposite. Each of the date scenes I described above were written in a single effort. There are some concept art images I have from when I was planning out this chapter, but I've produced very little to no final art up to now. I found the experience quite liberating, just writing the scene with no thought of what it "looked" like, and no concern of the technical limitations of SD to create visuals. It's a bit of a leap of faith... but I also think I've learned enough of the SD limitations and ways around it that I should be able to create appropriate visuals for the scenes.

Regardless... work on the 2nd week of Round 2 continues. I am working to write the draft of the remaining days "soon", then will shift my focus to generating the art.

Some concept art for the Ashleigh date scenes:




As always, thanks for reading this and Sucker Punch,
regards,
-insomniac

 

[1nsomniac22]

Finished drafting Round 2 Week 2

TL;DR - this is a monster content week. The story hits major crisis/inflection points.

Just to review - this was the content published in Round 2 Week 1

Round 2 [Day 30 - Day 44]:
week 1 [Day 30 - Day 37]
1499 lines dialogue
  - 709 chapter
  - 165 ashleigh
  - 205 destiny
  - 270 lilly
  - 150 gail

The additional content drafted for Round 2 Week 2

Round 2 [Day 30 - Day 44]
week 2 [Day 38 - Day 44]
4108 lines dialogue
   - 1092 chapter
   - 2255 ashleigh
   - 340 destiny
   - 135 lilly
   - 53 gail
   - 233 emily

This represents a massive effort. There are multiple routes through the Ashleigh story line (as stated in the last DevLog), but there is also an enormous amount of her story that is told in this week.

The sharp eyed will also see that a new character, Emily appears. Her story is critical to developing some of the darkest aspects of the main story arc.

I'm switching dev efforts from full time writing to image generation. Then there will be final edits and integrations (SFX, BGM, other visual effects). There's a lot to do still, but I'm feeling extremely satisfied with having completed the manuscript writing.

Sorry, no WIP pictures for this update.

Back to work for me, until the next DevLog, Regards,
- insomniac

 

[1nsomniac22]

Generating Visuals for Round 2 Week 2

TL;DR - focusing on generating the visual content for this release

Focusing full time on generating the visual content for the R2W2 release; but as with the dialogue, there's a ton of images to generate. I'm currently focused on completing the images for the initial date scenes for Ash & Leigh, then there are 5 different intimate scenes from those 2... it's a lot. And that's just Monday's content.

I'm going to have to beg patience as I work through all the scenes doing the visuals and edits. I don't have a realistic ETA yet. I shipped R2W1 on or about 20 Nov 2025... If I stick to my original release plans (1 week of in-game time every 2 months), that puts R2W2's release around Jan 20 2026... I will try, but with holidays... well, time is at a premium right now. I will continue to update the schedule in future DevLogs.

Here's some not-quite complete images captured from the Ash date scenes in R2W2:



But as always... back to work, Regards,
-insomniac

 

[1nsomniac22]

TL;DR - working through the scene visuals and edits

By my count, there are 16 main scenes in Round 2 Week 2. I've been working through generating the visuals and editing... and it's a lot. It took 3 entire days to "complete" the visuals for one of the more challenging sex scenes -51 total images so far- there are still 5 that need to be made/remade that are kind of frustrating me. That is one of the more involved scenes in this game week - overall I'm happy with how that scene came together. Another of the sex scenes clocked in at 27 images... so a bit less complicated.

I think (hope) the remaining sex scenes are less challenging/graphically dense (there are 4 remaining sex scenes in this chapter)... but there are some other non-sex scenes that are important to the story that are going to be challenging.

Two incomplete examples from one of the sex scenes in R2W2 that I've marked "done", (final clean up still needed):


Trying to stay on schedule for late Jan '26 release. Thanks for reading,
-insomniac

 

[1nsomniac22]

The Beatings Continue

TL;DR - images are out of draft for 5 of 6 scenes

Happy Holidays and all, but managed to knock out the initial visuals for another 3 Ashleigh scenes. The remaining scene is less technically complicated than most of the ones that are complete, but emotionally it has the highest burden. To make sure I'm clear headed going into it I'm pausing developing the sex visuals after I complete the current scene... which is needed. I've spent almost the entirety of the past working week focusing on sex. BDSM sex... vanilla sex... sex where both partners are fighting to assert dominance... it's been a lot of sex. Not that there's anything wrong with that .

Now, there's an entire weeks worth of other content I need to generate also; a lot of story element visuals need to be created and edited. That's where my focus is going to be for the next week while I decompress from... the... well... orgy.

So, before I return to image creation and editing, here are the current gallery images for the different scenes with Ashleigh - they're not exactly spoilers... maybe appetizers for the scenes that are included in the upcoming release.


As always, thanks for reading and your patience while I wrap up this sprint,
-insomniac

 

[1nsomniac22]

Progress... progress...

TL;DR - on schedule; edits and additional scene visuals progressing; discussion of UI changes.

With the drawdown of the holiday season I've been happily occupied with IRL things. Just now getting back into the swing of working on Sucker Punch.

• Monday: 1 of 5 Ashleigh routes is final edit complete.
• Tuesday: is final edit complete.
• Wednesday: There are 6 major scenes that are critical to the story (all routes); 4 are final edit complete, 2 are visuals and final edit in progress.
• Thursday: 1 major scene
• Friday: no major scenes
• Saturday: 3 major scenes
• Sunday: 4 majors scenes

So... there's still a lot of editing and minor visual work to do, most of the remaining scenes are character/dialogue scenes, so just character work which goes faster than full scene renders. The work is mostly charted and I'll keep punching out items on the list. So... what else is going on for this release? Actually, quite a bit.

Visual language - This project is an experiment in using new AI technologies in generation of VN's. Obviously Stable Diffusion has been leveraged in generation of all the visuals, and I've selected BGM's where AI was used in their creation. But for this chapter I have been leveraging and AI agent for other aspects; first:

The stat bar:

Ever since the original release I have not been happy with the stats screen displayed at the end of a Round. I had spent two days trying to figure out a way to implement my vision within the available widgets of Ren'Py, but, to no avail. The hbar concept isn't configurable to display what I wanted - a slider bar showing the stat within a range. So, spirits crushed I just shipped with the default bar showing how much of the "maximum" of a stat was filled.


The first chapters shipped used a balance score to represent which personality of Ashleigh is becoming more dominantly expressed. The score ranges from a negative to positive value. Not exactly what the hbar is designed to display, so I had to plan-B it and just show the raw number value and what it's supposed to indicate. Not very useful and not at all satisfying.

Over this development cycle I asked the AI agent how to implement a hbar to accomplish my design vision. To be honest, the first few attempts were not successful. The agent discovered the same limitations I had found. Then the agent went in a different direction than I had considered - it created a small custom displayable element to use instead of the built-in hbar. It still didn't work at first - it was rendering as a plain gray bar; but that was the eureka moment. I asked the agent to implement that bar with a specified number of color zones and it did so properly. It struggled a bit with the indicator - I had asked for it to present as a triangle and that's not easily implemented in the version of pygame that Ren'Py leverages. So, changed the indicator to a rectangle. Then I took the AI generated code and started modifying it further. The AI generated a function to calculate linear interpolation between two RGB colors to calculate the different zone colors. That was extremely useful - I changed the code so instead of 5 zones it would calculate 100 steps from each side of the bar (a gradient), then I updated the method to allow submitting the edge colors, the indicator color the max, min and current scores.


When I reviewed the new graphical element I was impressed. The AI agent and I knocked out something that I struggled with for 2 days in about an hour. And it's 90% of what my original vision was -the last 10% is a triangle indicator, which truth be told I don't care about anymore, the visual style of the rectangle works fine. I am so impressed with this new visual element that I'm replacing all the hbars with it - I just need to tweak the colors... which leads to item 2:

Visual language of the Sucker Punch:

I'll freely admit I'm a UI noob (it's not something I spend any time on IRL), so creating a consistent and natural visual language is a real challenge. I made some of the first halting steps already in the first chapters I shipped: the font choices, the fact that Leigh & Ash have different font types for their personas, the visual hint for important story choices:


Here, the red/orange indicates a negative choice and the blue indicates a positive choice - for earlier dialogues in the game this translates to positive stat increases - increase of trust or persuasion increases versus decrease of trust or intimidation increase.

This is a foundation, but there are other choices that affect other stats in the story where the design language can be more explicit. So the R2W2 release will introduce this new design language representing corrupting choices and choices that increase the MC's sadism.


These visual elements will be consistent through future chapters and on the stats screen. This was maybe a minor detour in the usual progress report, but if you're reading this, then it's hopefully a glimpse into ideas I've been shaping behind the scenes that should make the story and the choices more intuitive. Still pressing ahead with the work, still looking to be on schedule.

Thanks for reading, regards,
-insomniac