It has been just over two months since the game's release, and I have closely monitored player feedback.
In this update9
Full notes
Full DREAMIO: AI-Powered Adventures update
Read the full published notes in a cleaner layout. The original post stays linked below.
What changed
0 fixes1 addition4 changes0 removals
Server
Performance
UI and audio
Store
addedIn-game currency CensorshipTo address these concerns, I have added support for local inference. From now on, you will be able to run the game using only your own hardware. This allows you to use any LLM, Stable Diffusion, and TTS models, and also eliminates the need to pay for cloud services. Moreover, it's fully self-contained, so you don't need to install Python, separate server executables, or WebUIs (although support for external API endpoints is coming soon too).
changedText GenerationI have integrated llama.cpp directly into the game. This way, I get closer to the actual models and have full control over sampling. It runs on Vulkan, so no NVIDIA GPU is needed. It accepts models in .gguf format.
changedImage GenerationAlso integrated directly into the game with no dependencies. Runs on CUDA, so NVIDIA GPU is preferred. It accepts models in .ckpt, .safetensors, .diffusers, and .gguf formats.
changedRegarding Censorship and NSFW contentIt is not my intention to limit the actions you can take in the game. If the narrator rejects some of your actions (due to them being immoral, unethical, etc.), this is not the intended behavior and should be corrected by either adjusting the narrator's instructions or by switching to a different language model. However, as long as Steam prohibits certain types of content, including live-generated adult-only sexual content , hate speech, and others , the Steam version of this game will continue to censor these types of content, even when using local models. I am not trying to get the game banned from Steam again ; it has been hard enough to get here. Currently, Steam is not the place for live-generated adult-only AI games.
addedTo address these concerns, I have added support for local inference. From now on, you will be able to run the game using only your own hardware. This allows you to use any LLM, Stable Diffusion, and TTS models, and also eliminates the need to pay for cloud services. Moreover, it's fully self-contained, so you don't need to install Python, separate server executables, or WebUIs (although support for external API endpoints is coming soon too).
changedI have integrated llama.cpp directly into the game. This way, I get closer to the actual models and have full control over sampling. It runs on Vulkan, so no NVIDIA GPU is needed. It accepts models in .gguf format.
changedAlso integrated directly into the game with no dependencies. Runs on CUDA, so NVIDIA GPU is preferred. It accepts models in .ckpt, .safetensors, .diffusers, and .gguf formats.
changedIt is not my intention to limit the actions you can take in the game. If the narrator rejects some of your actions (due to them being immoral, unethical, etc.), this is not the intended behavior and should be corrected by either adjusting the narrator's instructions or by switching to a different language model. However, as long as Steam prohibits certain types of content, including live-generated adult-only sexual content , hate speech, and others , the Steam version of this game will continue to censor these types of content, even when using local models. I am not trying to get the game banned from Steam again ; it has been hard enough to get here. Currently, Steam is not the place for live-generated adult-only AI games.
It has been just over two months since the game's release, and I have closely monitored player feedback. The vast majority of the criticism has been related to two main issues:
In-game currency Censorship
To address these concerns, I have added support for local inference. From now on, you will be able to run the game using only your own hardware. This allows you to use any LLM, Stable Diffusion, and TTS models, and also eliminates the need to pay for cloud services. Moreover, it's fully self-contained, so you don't need to install Python, separate server executables, or WebUIs (although support for external API endpoints is coming soon too).
Text Generation
I have integrated llama.cpp directly into the game. This way, I get closer to the actual models and have full control over sampling. It runs on Vulkan, so no NVIDIA GPU is needed. It accepts models in .gguf format.
Image Generation
Also integrated directly into the game with no dependencies. Runs on CUDA, so NVIDIA GPU is preferred. It accepts models in .ckpt, .safetensors, .diffusers, and .gguf formats.
Speech Synthesis
I have integrated two options:
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech
Both options use Unity Sentis as the backend and run on any hardware.
Other
Depth estimation, speech recognition, and classifications all use Unity Sentis as the backend and run on any hardware.
It is not my intention to limit the actions you can take in the game. If the narrator rejects some of your actions (due to them being immoral, unethical, etc.), this is not the intended behavior and should be corrected by either adjusting the narrator's instructions or by switching to a different language model. However, as long as Steam prohibits certain types of content, including live-generated adult-only sexual content, hate speech, and others, the Steam version of this game will continue to censor these types of content, even when using local models. I am not trying to get the game banned from Steam again; it has been hard enough to get here. Currently, Steam is not the place for live-generated adult-only AI games.
Endless Replayability Fest
Dreamio will be participating in Steam Endless Replayability Fest on May 13-20 with a 10% discount!
