Heeeelp, I am new to using this program. I just recently downloaded the full version, and this error keeps appearing, and I don't know what else to do :c
That error happens when Thaluna tries to use GPU acceleration (PaddleOCR-GPU) but CUDA/cuDNN isn’t available on your system.
This is already fixed — the next patch will automatically switch to CPU mode instead of closing the app.
For now, you can fix it manually: 1️⃣ Go to the folder where Thaluna is installed. 2️⃣ Open the subfolder _internal. 3️⃣ Find the file config.json. 4️⃣ Open it with Notepad. 5️⃣ Find the line "ocr_device": "cuda" and change it to "cpu". 6️⃣ Save and restart Thaluna.
The issue you reported has been fixed in version 2.2 — Thaluna now automatically switches to CPU if GPU initialization fails. You can simply re-download the latest version and it should run fine👍
Manga mode needs some work. Mainly using it for JP->Eng manga translation and it can't seem to play nice with any Ollama models I give it. Still don't regret the purchase and am eagerly awaiting the next update!
I think I see what happened. In Lens Mode the OCR engine is designed for horizontal text, so if you’re working with vertical Japanese it can give messy input to Ollama models. That’s why things didn’t line up.
For vertical manga, the real-time mode with Settings → OCR Mode → Manga (Vertical Text) works much better. It won’t auto-box everything perfectly, but you can move the capture box between bubbles and it should give cleaner results. If it’s horizontal text, Lens Mode should already be fine.
I also plan to improve Lens Mode so it handles vertical Japanese properly in a future update — it’s definitely on my list.
By the way, when you said it “can’t seem to play nice with any Ollama models,” did you mean the translations came out as nonsense, or just random characters? That info would help me a lot to confirm if OCR was the real issue.
Thanks again for using Thaluna, and for taking the time to share your experience. Feedback like this really helps me improve the app, and I’m happy to hear you’re using it for manga.
I was mainly using the cropper next to the snapshot button. With the base model, it would kinda work, but I've got a decent pc so I tried hooking it up to some larger models. Gemma was hopeless and would just try to talk to me instead of properly translating, and more notably mistral kept either spewing out symbols (+kr, ++__++ and such) or saying that there's nothing to translate.
I did have it set to vertical, though I didn't use the drag box much as it kept getting distracted.
Gonna try hooking it up to my best boy DeepSeek to check if it's just the models being weird.
Hoping for your success, this shit is groundbreaking.
Thanks a ton for testing all that, really appreciate it In my case Gemma 3:4B actually worked fine for translations, but yeah, it can vary a lot depending on the text/setup. Super curious how DeepSeek will work for you!
← Return to tool
Comments
Log in with itch.io to leave a comment.
Heeeelp, I am new to using this program. I just recently downloaded the full version, and this error keeps appearing, and I don't know what else to do :c
Hey! 😊 Thanks for reporting this.
That error happens when Thaluna tries to use GPU acceleration (PaddleOCR-GPU) but CUDA/cuDNN isn’t available on your system.
This is already fixed — the next patch will automatically switch to CPU mode instead of closing the app.
For now, you can fix it manually:
1️⃣ Go to the folder where Thaluna is installed.
2️⃣ Open the subfolder
_internal.3️⃣ Find the file
config.json.4️⃣ Open it with Notepad.
5️⃣ Find the line
"ocr_device": "cuda"and change it to"cpu".6️⃣ Save and restart Thaluna.
After that, it’ll work normally
The issue you reported has been fixed in version 2.2 — Thaluna now automatically switches to CPU if GPU initialization fails.
You can simply re-download the latest version and it should run fine👍
Manga mode needs some work. Mainly using it for JP->Eng manga translation and it can't seem to play nice with any Ollama models I give it.
Still don't regret the purchase and am eagerly awaiting the next update!
Hi,
Thanks a lot for your feedback 💜
I think I see what happened. In Lens Mode the OCR engine is designed for horizontal text, so if you’re working with vertical Japanese it can give messy input to Ollama models. That’s why things didn’t line up.
For vertical manga, the real-time mode with Settings → OCR Mode → Manga (Vertical Text) works much better. It won’t auto-box everything perfectly, but you can move the capture box between bubbles and it should give cleaner results. If it’s horizontal text, Lens Mode should already be fine.
I also plan to improve Lens Mode so it handles vertical Japanese properly in a future update — it’s definitely on my list.
By the way, when you said it “can’t seem to play nice with any Ollama models,” did you mean the translations came out as nonsense, or just random characters? That info would help me a lot to confirm if OCR was the real issue.
Thanks again for using Thaluna, and for taking the time to share your experience. Feedback like this really helps me improve the app, and I’m happy to hear you’re using it for manga.
I was mainly using the cropper next to the snapshot button. With the base model, it would kinda work, but I've got a decent pc so I tried hooking it up to some larger models. Gemma was hopeless and would just try to talk to me instead of properly translating, and more notably mistral kept either spewing out symbols (+kr, ++__++ and such) or saying that there's nothing to translate.
I did have it set to vertical, though I didn't use the drag box much as it kept getting distracted.
Gonna try hooking it up to my best boy DeepSeek to check if it's just the models being weird.
Hoping for your success, this shit is groundbreaking.
Thanks a ton for testing all that, really appreciate it
In my case Gemma 3:4B actually worked fine for translations, but yeah, it can vary a lot depending on the text/setup. Super curious how DeepSeek will work for you!
Great tool, you've done a great job, keep it up!
Are there any plans to implement this on Linux? Since I definitely won't be using Windows,
it would be a shame if there were no Linux version.
Thank you so much for the kind words! Thaluna currently works on Windows, but I’ll see what I can do about a Linux version down the line.