Home Creators Posts Import Register Favorites Logout
haven't archived this post yet. have a subscription? use the importer!

Content

✨ stable diffusion:
- changed folder structure: files are now distributed into cuda, darwin, vulkan folders, models in the models folder
- default model converted to gguf: ~1-2 seconds faster on gpu and about 10% faster on cpu, build is 2.7 gb smaller (yay)
- added support for amd cards: app auto-detects the card and uses vulkan instead of cuda
- improved location detection and memory
- updated loras in the win-local build
- rebuilt for mac and amd cards; increased graph sizes
✨ koboldcpp:
- updated to version 1.95.1
- koboldcpp remote: added ngrok support as an alternative to cloudflare
- fixed bots: for detecting outfit changes and location; to generate image prompts
✨ added rounded mplus 1c font as default
✨ added photo studio location
✨ desktop: added button to hide character and text, hotkey shift+h
✨ added grok 4 model (still unstable but interesting in places)
🛠 lora: tweaked system prompt for image generation
🛠 input field improved for easier entry of large multiline text
🛠 adaptive font sizing adjusted: text now fits more often without scrolling
🛠 help section updated
🛠 quick menu now shows only icons
🛠 updated icons for saving images and phone
🛠 settings: tabs now hide when clicking anywhere on the tab bar, not just the icon
🛠 fixed save-image button in nvl mode
🛠 removed gemini recommendation text from main screen
🛠 suggestions (quick replies): now use the last 4 utterances instead of the entire dialogue
🛠 openrouter: fixed error when selecting models from dropdown
🛠 cosmos: added cosmosrp-3.0 and cosmosrp-3.5 models; removed deprecated ones
🛠 anthropic claude: fixed empty “: ” message error with small bots; suggestions (quick replies) now work
🛠 cohere: added suggestions support
🛠 rewritten location detection bot: now triggers immediately after the trigger, not on the next “turn”

→ mega
→ gdrive

→ ngrok plugin (see koboldcpp-remote instructions in the help section)

for low-end machines, i quantized a more heavily compressed q5 model; it should be a bit snappier.

upd: the windows build has been re-uploaded.
if u downloaded the build earlier and are getting an error - this patch is for nvidia: put dll files in the resources\stablediff\cuda folder

for mac it’ll be next week

Files

Previews only

Comments

Chadin Uransathien

stable diffusion is error sd exit3221225781. but no pronlem with 0.5.0.4 version

Anarchitect

I accidentally hit enter on a text field while an image was generating, you might want to make it wait on the text entry until the image was done. Also, a lot of the generated images are pretty weird, it seems to mix details that I put in about my character with the NPC's - so if I put "muscular arms" I get some sort of half-Fiona with muscular arms. I'm not sure if I should leave the positive field blank for now or what?

Anarchitect

You might think about making Loras for each character and turning them on/off dynamically. Another thing to try is area mask conditioning - applying the conditioning to certain areas will isolate things like a description of the player character to just that area.