Every choice transforms your body and shapes your adventure · By
Tried and it's still broken but acts as if i had set it to 800 when it's really at 1024 (aka every page acts like it's the start of the game)
For reference, i had a save at page 160 ish earlier and there was no problem at all. The classic games seem to be working sort of so i honestly don't know why mine is acting out. 🤷♂️
Yeah, it's definitely a pain point for me. I've observed when running a local AI on qwen2.5-7b-instruct-uncensored, the performance is *slightly* more reliable, but it's definitely not perfect. Qwen is about the most stable I've used (out of over a dozen _instruct_ tagged models). I mostly just disable stat prompts now and try to construct scenarios in a way that they aren't required. The AI is actually surprisingly good at conjuring skill checks and resolving them without including the details in its response, in a way that keeps the game immersive.
First thing to check is if your scenario still works when you remove the new stat. If you continue to get the error, that means you have instructions somewhere that are causing problems.
I would check the "name" for the actual stat, as I didn't see any kind of key sanitization in the source code. If you've added a double-quote in the name for your stat, it might be interfering with some behind-the-scenes code.
Next place to check would be the description for the stat, as well as the ranges. If those are clear, check if you're using the custom stat progression box (the one that lets you add Javascript).
And if all of *that* is good, then you should export your scenario and try it on the desktop version. You would do this by trying to export somewhere like Google Docs so that you can import it from the desktop client.
Beyond that, FieryLion may have more ideas. Those are mine as a web developer. I see this error frequently with my day job when someone doesn't pair quotes or tags correctly.
WARNING!!! VORNY TALK AHEAD!!!
The stat was "Digestion" the description: "Represents how long it'll take before the prey is digested after being Vored. If the player is the prey, damage Health by 25 every page once Digestion reaches 100."
Or something like that ... as for if it works, the world works perfectly (sort of) without said stat.
I removed the stat after a few tries, currently ensure how to make it work as intended since it wouldn't increase unless i said "i watch as Digestion meter increased" or something like that.
I'm not the best at this type of stuff ... I mean heck, my world is an altered version of Braduhsley's named player Colossus world... (with alot of new junk and less furries and more monster girls) 😅
I'd like to fiddle more and give you some examples, but Windows has suddenly decided to treat this game as a virus and refuses to let me run it.
This is my "best guess" for trying to adjust the System Prompt for your scenario after poking at my local QWEN-2.5 AI on this. This assumes the "Digestion" stat is being tracked on the prey (in this case, the player) and not the predator (the NPC that has swallowed the prey).
Text to add to your prompt:
### Detailed Instructions
#### Digestion
- **Initial Value:** The digestion timer starts at zero.
- **Increment:** Each time a creature swallows another, digestion begins.
- **Decay:** Digestion decreases by 10 every action that does not involve swallowing.
- **Threshold and Effect:** Once the digestion reaches or exceeds 100, damage Health by 25 with each subsequent action.
This is why running a local AI is so good. The downside is that you're hardware and instruction limited--AIs behind web endpoints are generally more "up to date" and may have "guard rails" in what they're allowed to generate depending on laws in your locale, even if you pick one that is labeled "uncensored".
Well, the good thing is it worked, the bad thing is it also didn't because now there's too much text... I'm using the basic/default due to me preferring it's role-playing capabilities but this also means 3900 cap... and apparently describing the different types of Vore is too much for that in some locations that have alot of entities... (even without the Vore description, the digestion stuff by itself is a bit too much for some areas) 😅
Lemme go count my entities rq
Edit: 67 ... I have 67 entities if you don't count the 3 actions, minus 2 if you don't count the location specific ones. 😅
Edit The Sequel: Wait would it be better if I added the vore variants into the description of the entity Vore (action)? Since it's an action and not an entity present in every area, would it smooth out the kinks? (Pun intended)
If you're running a local AI now in LM Studio, there is a gear icon in the "Chats" tab of LM Studio. If you go into the "Developer" tab in the left panel and select your model in the center panel, the right panel has a "Load" tab where you can adjust the token length the local server will allow. Changing this value does require you to reload the model in LM studio (it gives you a button prompt for this), and bigger values require more CPU or GPU.
As far as resolving your entity behavior, I haven't looked _that_ deeply into the source code. I think the game only sends entities based on the player's location, and this goes out with the <LOCATION JSON DATA> placeholder in the various prompts. So if all 67 of your entities are in the same area, it might be part of why you're hitting some token limits.
I've had the "best" success by trying to define behaviors and states in the System prompt (I think I pasted an example for the Slime Core and Player Excretion above) and then mentioning those behaviors in the entity's AI instructions (second box on the Entity setup), but I've never had more than 4-5 "weird" behaviors in a scenario that I needed to explain as part of the instructions.
I tried it today and it's fine for now... not sure what it was but it made bug testing my world very annoying lol.
Edit: It appears I have accident found the root cause, it's the xenomorph world in the shared worlds. Downloading it causes the worlds to get Thanos snapped when you exit world editing or the world you're playing in. I would assume it also causes the character bug though I'm not sure due to that world's lack of model. 🤷♂️
default AI has very little memory to work with, you should use your own models or make a free OpenRouter account to use better AI with more memory https://fierylion.itch.io/formamorph/devlog/885513/quick-setup-guide-free-openrouter-setup
here is virus total scan results of the game file, 64/64 scanners passed it https://www.virustotal.com/gui/file/5b8a6e3f61dc6e64ec00fb24e05da14ad4d9d2068ab054454e3f35efc383a906
so yeah, this error is because the new AI is too fast (I improved AI writing speed by 5-10 times). I discovered a bug in the game code that caused it to fail when parsing AI responses that are too fast. I have patched the bug, but I cannot patch old versions that you have downloaded. You’ll need to use the latest version unfortunately. I can’t just slow down the AI response for older unsupported game versions.
this is a common issue with smaller AI models like mistral nemo, you should use a bigger model such as one of the free models on OpenRouter. A quick fix is to edit the AI message to remove the redundancies (if you leave the repeating stuff in, the AI will look at your message history and likely write more repeating stuff later on…)
FieryLion summed it up pretty well. I've played with models under 20b parameters mostly, and they repeat themselves *frequently*. They'll basically blueprint or template part of a message and just keep pasting it back in like it's boilerplate. I had pretty good success with a 30b parameter Gemma fork running locally (I'm on a 2070 Super with 8GB VRAM), although I only get 3-5 tokens per second (super, super slow). But the dialog quality was absolutely stunning compared to the 8b and 14b models. Qwen 2.5 is listed in several places as a "potato-friendly" model, but it's very unsophisticated: it can't really handle lewd/suggestive content in anything that would titilate or suspend disbelief, it is very repetitive and subject to "GPT-isms", and even if you set it for high temperature and sampling (to add a lot of randomness and creativity), it's still heavily constrained by how small it is.
I _personally_ don't like running AI through a hosted endpoint, even though I could be using some really good hardware and getting really fancy models out of it. My two main reasons are privacy and cost. But if you want better quality responses, you're going to have to either pay for much better hardware or hosting solutions (such as OpenRouter).
I've found that it's not always reporting an error properly in the LM Studio when the AI's context length just barely isn't enough, and it goes off trying to generate a response anyway. This is what's caused spontaneous scenario resets for me, mainly on very big/detailed worlds.
Try increasing the context length a little bit and see if that changes it.
Yeah, basically what FieryLion said. Even the web version's AI is dependent on a Context Length set on the ai host, though in the web version you'll obviously not have access to it. (For reference, Context Length is simply how much data the AI is configured to be able to handle at a time in a single request, action prompt + system prompts + world rules/stats/entities/location data etc)
The fact it happens on all worlds for you seems unusual though, so my hypothesis is uncertain there as I've only experienced it on heavy worlds.
Basically, my hypothesis was that if say, the AI was configured to 4000 token context length, and a world required 3950, the buildup of memory containing history, or the Notes, could push it past 4000 in an edge case the AI isn't configured to react to since, just maybe, it only checks token limit BEFORE taking into account history, causing it to discard all past history and reset the scenario to fit within the configured 4000 token limit. But eh, I don't really know the inner workings enough to really say anything certain, which is why I'm just hypothesizing something that could logically explain what's happening, since increasing context length HAS worked for me.
it looks like your context length might be wrong, check your context length setting in LM STudio. Make sure context length is larger than the in game setting for max output tokens + max memory
All right, seems to work. So this max memory, is it the previously generated text? Do the world settings (locations, descriptions, etc) consume it?
Also, would you answer a few more questions i have about how the program works? The definitions for game world, stats, entities, locations and dictionary, are they sent with every prompt or only at the start of the game?
Hi I'm experiencing a problem with trying to save my worlds and I want to ask if it is possible for you to make it that you can save them offline on mobile or make a mobile version of the computer app? Also thanks for the good job you're putting in to create this awesome game. 
No download gives me this. I'm on opera. 
This is the result on Firefox. The world's don't even load. 
did something happen 