From official channel:

Links

• HiDream O1 on Civitai: civitai.com/models/2618495
• Hugging Face: HiDream-ai/HiDream-O1-Image
• GitHub: HiDream-ai/HiDream-O1-Image
• Technical report (PDF): HiDream-O1-Image.pdf

What is HiDream O1?

HiDream O1 is an open-source image foundation model released by HiDream-ai. The headline features:

• One model, three tasks. The same checkpoint handles text-to-image, instruction-based editing with a single reference image, and multi-reference subject-driven personalization with up to ten reference images. The mode is selected by what you pass at inference — no separate adapters or LoRAs required.
• Native 2K. Direct 2048×2048 generation with no upscaling.
• Text rendering that actually works. 0.979 / 0.978 on LongText-Bench (EN / ZH), 0.90 on GenEval for compositional prompts, 89.83 on DPG-Bench for dense prompts.
• Permissive license. MIT.

Stolen from here: https://civitai.red/articles/30301

A handful of updates to share this round. New ways to tell a story, new ways to get featured, new things in the generator, and a fresh way for community curators to highlight great work.

All of the following is live now.

📚 Civitai Comics

We launched Civitai Comics so you can tell your story page by page. Thousands of comics have already been made. Not everything is published yet, but it's a strong start. The full article has all the details on how it works.

🖼️ Featured Image Requests Have Been Removed

This one is subtle, and most of you probably never noticed it. Underneath the featured images on the homepage, there used to be a way to request that an image be featured. We're not pursuing that flow anymore, so we've taken it out.

If you want to get on the homepage, the most reliable approach is to make great images and post them. The next item below also opens up another path.

🎲 Featured Images: More Variety

Featured images used to be a fairly random pull from the most recent images added to featured images and curated collections. We tightened the logic so a single creator now appears at most twice in any pull, and the order shuffles more aggressively. The result is more variety from more creators on the front page.

🎬 LTXV Sulphur in the Generator

Sulphur dropped last week and is already available in the generator. Try it out.

⚡ LTX Promo: Video From 35 Buzz

LTX video generation now starts at 35 Buzz. That's cheaper than generating an image with some models.

Members can also generate multiple LTXV videos at once:

• Bronze: 2
• Silver: 3
• Gold: 4

🌟 Featured Collections

We quietly rolled this out a little while back without making noise about it: select community collections now get featured on the homepage. That means more curators than ever are looking for ways to surface up-and-coming artists and other great creators, with taste from a variety of perspectives.

If you'd like to be considered as a featured curator, reach out at hello@civitai.com.

Big thanks to our first curators: Cinnadust, Snilek_Robotka, vishnarjk, purplelady, Daalis, and Alexia_Rousse.

<<Thank you

Three months of late nights from the team to get this in front of you. Thank you for being the kind of community where we can ship a beta this ambitious and trust you'll meet it where it is.

Now go make a comic. Tell a story. Show us your world.>>

How to get it:

• Browse: civitai.com/comics
• Make one: civitai.com/comics/create
• Same on civitai.red if that's your door.

How it works

Step 1. Spin up a project at /comics/create. Give it a name, a genre, a cover. Drop in your references: characters, locations, items, styles. Anything you want to stay consistent across pages goes here. We've made it really easy to iterate within the generator and then pull anything you've made as a reference.

Step 2. Build a chapter. Either use Smart Create — type a story, pick a panel count, let it plan the page — or build panel by panel. Pick the model you want per panel: Nano Banana, Flux.2, Seedream, Qwen, Grok, OpenAI's image model — take your pick.

Step 3. Iterate. Open any panel in the editor, mark it up, paste in another image, drop a speech bubble and say what you want it to say, <<@-mention>> a reference to keep your character consistent. Publish the chapter when it's ready, or schedule it, or gate it behind Early Access for your fans.

What's in the box

• Smart Create — describe a story, get a chapter back. Tweak the panel prompts before you generate.
• Iterative editor — annotate, mark up, paste reference images, drop speech bubbles with custom text. Image-to-image with intent.
• References — Characters, Locations, Items, Styles. Build them once, <<@-mention>> them anywhere.
• Seven image models — Nano Banana, Flux.2, Seedream v4.5, Seedream 5 Lite, OpenAI GPT-Image, Qwen, Grok Imagine. Pick per panel.
• Cover + hero image generation — make a cover that matches your comic's vibe without leaving the editor.
• Layouts — pick a page layout, an aspect ratio, set the hero panel's focus.
• Publish your way — go live now, schedule it, or run an Early Access window where fans pay Buzz to read early.
• Export — pull a chapter down as a PDF or the standard CBZ (Comic Book Archive) format.
• Browse + follow — read what the community is making, sort by newest, most-followed, or most chapters, follow the creators you like.

Now go make a comic. Tell a story. Show us your world. 

P.S.: “I already know some of you are going to say, "Why are you releasing new stuff when the site is still broken?!!! 😡". We're still working on it, and this week we're slated to make a few of the biggest moves that will hopefully solve the source of a lot of the complaints. We've just got too many things that I'm excited to share with you all, so I didn't want to wait any more.”

the price of the second image is on Civitai = free.

⚠️(!) ATTENTION (!): Only works WITHOUT Enhanced Compatibility.

Works for:

SD 1.5, SDXL, Pony, Illustrious, NoobAI, Flux.1, Anima, Z-Image, Flux.2 Klein

Special thank you from one of the founders of Civitai @ JustMaier:

"The reason we can afford to run a promo like this is because the people using Civitai keep showing up, keep creating, and keep making this whole thing worth doing.

Go make something. Then make it again, for free."

https://civitai.com/articles/29076/two-for-one-every-generation-twice-the-output

…Not so "extra".... 2 days late....