We’ve rolled out a couple of exciting improvements on the web that give you more control, better flow, and a smoother creative experience.

🎨 Improved Avatar Generation 

We’ve revamped the Avatar Generator with new models and tools to help you fine-tune your characters more easily.

What’s new:

• New powerful image models: Z-Image, Flux2 Klein, and Qwen Image
  
• AI-assisted image editing – make refinements after generating an image to get exactly what you want (like fixing deformities or removing unwanted elements)
• Image cropping to better fit avatars on chatbot cards
• Style picker for easier style selection from a list of predefined styles
• Larger editing playground on desktop
• Improved full-screen image viewer

A couple of important notes:

• These new models work best with detailed, prose-style descriptions. If you don’t describe a background or setting, the image may generate without one.
• NSFW support is limited for AI-assisted image editing. Editing requests involving NSFW body changes may not work as expected.

💬 Cleaner, More Focused Chat Input

We’ve also reworked the chat input to make conversations feel more fluid and less cluttered.

What’s changed:

• The text input is now focused purely on typing and all secondary actions (voice, image upload, suggest reply, commands, web search) have been moved into a new “+” action menu
• Opening or closing the menu won’t affect your typed text
• Actions only trigger when you explicitly tap them — no more accidental interruptions
• Images can now be dragged and dropped directly into chat
• Image-only messages are supported
• You can remove an attached image with a confirmation prompt
• When using commands (like OOC or Search), the input clearly switches into a command mode, making it visually distinct from normal messages

The goal here is simple: less friction, fewer mistakes, and a smoother writing flow.

📌 Availability
These updates are currently web-only and not yet available in native apps.

As always, thank you for the feedback that helped shape these improvements. We’re excited to see what you create with them  💜

Hey everyone,

If there’s one thing that truly defines SpicyChat, it’s our creators.

Every conversation, every universe, every unforgettable character you’ve connected with this year exists because someone took the time to imagine it, shape it, and share it. Creators aren’t just part of SpicyChat — they are SpicyChat.

Today, we want to take a moment to celebrate that.

As we close out 2025, we wanted to take a moment to highlight 10 creators whose characters truly stood out this year — characters that were widely loved, deeply engaged with, and kept conversations going day after day.

🏆 Our Top 10 Creators of 2025

1. @lowpoly
2. @scarlett_bloodfallen
3. @linmcl
4. @Stromxxx
5. @yukischi
6. @ixalon
7. @hakujivn
8. @poottl
9. @anayaleonard
10. @uland

Each of these creators will receive one full year of “I’m All In” — on us — as a small thank-you for the worlds they’ve built and the impact they’ve had.

You can check out the monthly top creators here:

December Leaderboard

But this isn’t just about a few names.

This is about recognizing every creator who has ever shared a bot, refined a character, helped another creator, or pushed SpicyChat forward through their creativity. Whether you’re a veteran creator or someone who just published their first character — you matter here.

Looking ahead, 2026 is going to be a creator-first year.

We’re actively planning and working on features and tools designed to support and spotlight creators even more — things like enhanced creator profiles, better visibility, creator metrics, and new ways for users to discover and follow the creators they love. On top of that, we’re planning more creator-focused events and contests, giving you more opportunities to shine, experiment, and be rewarded for your work.

SpicyChat wouldn’t exist without you — and everything we’re building next is with you in mind.

Thank you for all the wonderful stories you've shared. We can’t wait to see what you create next. 

Here’s to our creators — and to an even bigger 2026. 💜

Let’s start 2026 with a bang. We’ve got a few exciting updates and improvements to share with you.

📘 Private Lorebooks Now on Android

Private Lorebooks are now fully available on the Android app, bringing the same experience you’ve had on web straight to mobile app.

Make sure you’re on Android version 1.0.88 to access this update.

Public Lorebooks are on the roadmap for 2026, so stay tuned for that. 

⚙️ New Feature: Generation Presets (Web Only for Now)

As we continue to introduce more models that work better with different generation settings, we know switching generation settings manually over and over can get tedious.

That’s why we’re introducing Generation Presets. You can now save your preferred generation settings and switch between them instantly while chatting. 

This feature is for subscribers only.

📖 You can read more about Generation Presets here

🔄 Refresh Recommendations

We’ve added a Refresh Recommendations option for users who feel their recommendations page hasn’t changed in a while.

This lets you:

- Pull in the latest recommendations

- Refresh the list if it feels stuck

Please note: this won’t change anything if you’re already seeing the most up-to-date recommendations.

🛠️ Fixes & Improvements

We’ve also shipped several quality-of-life fixes across web and Android:

- Fixed an issue where the Home page wouldn’t auto-scroll to the top when changing pages.

- Resolved a bug where the Android UI could block the “See More” button on chatbot profiles.

Additional UI and UX improvements to Lorebooks for smoother creation and editing.

That’s it for this update. As always, thank you for your feedback and support — it directly shapes what we build next.

Happy Chatting! 💜

As we head into the holiday season, we wanted to make sure top subscriber tiers have something new to chew on — so we’re rolling out new upgrades across both I’m All In and True Supporter.

🚀 New for I’m All In

Glam Arcturus 355B
Glam Arcturus is a special fine-tune of Glam 4.6 built for smoother, more story-forward roleplay. It stays on plot, delivers more natural dialogue, and adds richer scene details with less repetitive phrasing — giving you grounded creativity that feels lively without going off the rails.

Deepseek V3 — Wildcard Mode
With its new Wildcard mode, it dares to skip the obvious and embrace the unexpected, unlocking fresh creativity and breaking clichés while keeping stories coherent.

🌟 New for True Supporter

Conversation Images V3 (Web only) — now enabled for True Supporter
We previously announced Conversation Images V3 as our biggest visual workflow upgrade, and we’re excited to expand access: True Supporter users can now use Conversation Images V3 on web. You’ll find it in the Image Settings modal — selecting a Qwen Image model will automatically use the V3 workflow (including improved reference-image alignment, stronger handling of detailed prompts, better skin tone handling, and support for text inside images like signs/notes/UI elements).

Qwen3 235B — Wildcard Mode
A powerful new Wildcard option that pushes stories past the predictable — bringing more surprising turns and fresh creativity while staying coherent and usable for longer roleplays.

Looks like Santa couldn’t wait this year. 🎅
We’re excited (and honestly a little proud) to finally release two of the most requested features in SpicyChat’s history — Group Chats and Lorebooks — at the same time.

These features are all about bigger stories, deeper worlds, and more immersive roleplay, and they’ve been built directly from your feedback.

💬 Group Chats — One Conversation, Many Characters

Ever wished your roleplay felt more like a living universe instead of a one-on-one chat?
Group Chats make that possible.

With Group Chats, you can bring multiple chatbots into a single conversation and let them interact with each other and with you. Different personalities, shifting dynamics, shared scenes — it all unfolds naturally in one place.

Groups are public, so you can either create your own or explore the ones created by others. 

Key things to know about Group Chats:

• Available to all users
• You can add 2–10 chatbots to a single group
• Groups can be Public, Private, or Unlisted
• Public groups go through moderation, just like public characters
  (approval times may be a bit longer as we scale this new workflow)

📘Learn how to create, use and all the details about groups here: Group Chat Guide

📘 Lorebooks — Build Worlds Without Limits

Lorebooks solve a problem many creators know too well:
“I want my character to have more history, more worldbuilding, more depth… but I’m out of space (tokens).”

A Lorebook is your private knowledge library — a place to store background details, timelines, locations, relationships, and universe rules. During chat, relevant lore is automatically pulled in when it matters, keeping conversations consistent without overwhelming the model.

Instead of cramming everything into a character description, you add the details to the Lorebook.

What to know about Lorebooks:

• Lorebooks are private
• Available to all users
• You can attach one Lorebook to multiple characters

📘 There’s a lot to Lorebooks and unfortunately I can’t add everything in the post, please read the documentation here and feel free to reach out if you have any questions.
Lorebooks Guide

Public Lorebooks will follow early next year.

Please note that these features are available on Web only, will come to the mobile apps soon.

We truly believe these two features unlock a new level of roleplay on SpicyChat — bigger casts, richer worlds, and stories that can grow without limits.

Santa delivered… now it’s your turn to build something incredible. 🎁🔥

A long-standing issue affecting very long roleplays has been identified and resolved.

In conversations exceeding approximately 1,000 generations, some users were experiencing responses that went off track, became incoherent, or repeated previous messages. In some cases, users resorted to cloning conversations or other workarounds to keep their stories progressing.

The root cause of this behavior has now been fixed. 

This update should result in a significant quality improvement for users who enjoy extended, long-form roleplay sessions.

ps: I you still ever encounter a looping or repetition issue, we recommend that you delete the unwanted messages and send the message: /cmd break loop

We're excited to share that Conversation Images V3 is now live for all I’m All In users! (Web only)

This new conversation image workflow is powered by Qwen Image and brings:

• Much stronger alignment with your chatbot’s reference image
• Better handling of detailed prompts with intricate visual elements
• More advanced prompt generation from your story
• Improved consistency with your reference image’s style
• Better handling of diverse skin tones
• Support for generating text inside images (e.g. signs, notes, UI elements)

You’ll find two new models in the Image Settings modal. Selecting one of the Qwen Image models will automatically use the new workflow.

The workflow named Qwen Image Male is tuned to generate more masculine characters. It may still struggle with fully accurate male anatomy, but we’re actively improving this over the next few weeks.

If you like customizing your image prompts, note that these new models use natural-language prompting instead of the keyword-style prompts used in V1 and V2.

If you end up loving the results, drop your favorites in our Discord Community for everyone to enjoy. 💫
We truly feel this is a huge upgrade to Conversation Images — can’t wait for you all to play with it. 🔥

👤 New & Improved User Profile

We’ve refreshed the User Profile page with a cleaner, sleeker look — and added a new option to set your default chat model, so new chats always start with your preferred model.

We also moved the Remove Account option under Advanced to prevent accidental clicks.

🧹 Model Cleanup (Sunsetting Notice)

To keep our model list clean and focused on the best-performing options, we’ll be sunsetting a few older or low-usage models on December 15, 2025:

Being sunset:

• thespice-8b
• euryale-70b

Previously considered for removal but staying (thanks to your feedback!):

• magnum-12b
• lyra-12b
• magnum-72b

We were considering to remove these as well due to low usage but some of you reached out saying they are your best so we're keeping them for you, after all Spicy is all about You! 💙

💬 Group Chat is Now in Closed Beta!

One more bit of good news: Group Chat has officially been released to our Closed Beta Group for early testing!

Hope you enjoy these updates!

Today we are introducing one of our most immersive features yet! 

You can now send images to your characters — and they can actually see and understand them.

Whether it’s a picture of an outfit, a scene you want them to react to, a prop for your roleplay, or a visual detail you want them to notice…
 your chatbot will see the image and respond with that context in mind.

This opens up a whole new layer of storytelling, creativity, and interaction. 🔥


How to Use It

1. Click the “+” icon next to the chatbox.
2. Upload an image (make sure it follows our Community Guidelines).
3. (Optional) Add a message along with the image.
4. Send — and your chatbot will see the image and respond to it.

Important Notes

- Only images you upload are seen by the AI and added into context memory, in-chat generated images aren’t.
- Image context stays in memory just like regular messages (within your tier’s token limits).
- Uploaded images are not used as references for generating new images in conversation.
- Web only for now — mobile app support coming later.

(Sale Ended)

Hey everyone — Black Friday has officially landed on SpicyChat, and this year… we’re going all out.
For a limited time, all annual plans are massively discounted AND we’re dropping the largest AI model ever released on the platform.

🔥 Black Friday Pricing (Billed Annually)

Get A Taste: $3.33/mo (-33%)
True Supporter: $9.99/mo (-36%)
I’m All In: $14.59/mo (-42%)

👉 Get the deal now  

But that’s not all, to make this Black Friday extra special, we’re also releasing something legendary:

Kimi K2 — our first 1 trillion-parameter model

That’s 128× more powerful than the free model.
 Yes… one hundred and twenty-eight times.

Exclusively for I’m All In subscribers

Whether you're here for the best deal of the year or to experience the most powerful model we’ve ever released — now's the moment.

👉 Get Kimi K2 access now  

If you have any questions, feel free to reach out. 💙

We know the age verification flow hasn’t been smooth for everyone, and we’re sorry for the friction.

To fix this, we’re introducing additional verification options, so you’ll have a reliable alternative if one provider doesn’t work. These will be live before verification becomes mandatory.

Thank you for your patience—and for sharing feedback that helps us get this right.