Stable Diffusion online AI

AI-generated 🖼️🎬• Large Language Models ✒️ • open-source

[Stable Diffusion online AI @ai_diffusion]

Make a beautiful image with Qwen-Image 2.1: settings measured on the same seeds

https://t.co/NL5AFKr0Yl

[ComfyUI @ComfyUI]

Introducing MOSS Image MAX ULTRA HD, the latest post trained image model by the ComfyUI research team.

MOSS Image MAX MEGA ULTRA HD scores an impressive 1238 on our first party 4k anime characters with massive animal ears benchmark evaluations.

We believe so much in open models that we decided to open it before it's ready.

Kidding aside this is a test lora for MOSS Image that you can use to generate better high resolution (up to 10MP) images with MOSS Image with a bias towards anime but there was a lot of photographs in the training set.

Link to the lora here: https://t.co/VRlr5JXb4k

Give it a try and let me know if we should do more of these.

[ComfyUI @ComfyUI]

MOSS-Image is now supported in ComfyUI

@OpenMOSS dropped an open-weight image model that has blown up across the community. It’s a 5B model that renders legible text, accepts structure layout prompts and has a high bar for aesthetics.

The community has already been cooking up finetunes and LoRAs while the Comfy team has been working to support the model to run seamlessly on any consumer hardware.

This model is a must try - check it out.

[Hugging Models @HuggingModels]

Meet MOSS-Image-SFT-8-steps-dmd: a lightning-fast text-to-image model that generates stunning visuals in just 8 steps. Built on OpenMOSS-Team/MOSS-Image-SFT, it's fine-tuned for speed without sacrificing quality. Perfect for creators who need results fast.

[Photogenic Weekend @PhotogenicWeekE]

FLUX 3 Image Klein、Workflowも含め当初からいろいろ変わってるので要チェック！
https://t.co/YiInHFxrvM

[Stable Diffusion Tutorials @SD_Tutorial]

MOSS Image 👇 ComfyUI support

ComfyUI repacked official weights for better results:
https://t.co/HD2tpOJbkS

Pull request:
https://t.co/n29Ox8TfD7

[Black Forest Labs @bfl_ai]

Hey everyone,

We've updated our FLUX 3 Image Klein workflows to fix some issues and help you get the best results from the model.

• Update to @ComfyUI v0.41.3 and use our updated workflow, link in thread.
• We've updated the @huggingface Space as well.

To get the best results, the model should be used with our prompt upsampling and 2K resolutions.

If you can’t use our prompt upsampling, we’ve also made the recommended system prompt available in our repo to use in your workflows.

Thank you for the feedback everyone!

[Hugging Models @HuggingModels]

Meet FLUX-3-Image-Klein_GGUFs: a quantized version of Black Forest Labs' FLUX 3 Klein for ComfyUI. GGUF format means low VRAM and fast setup. Text-to-image and image-to-image in one model. Perfect for creators on modest GPUs.

[Hugging Models @HuggingModels]

Meet Qwen-Image-2.1-Uncensored-GGUF: a text-to-image model that turns your prompts into stunning visuals. With over 2 million downloads, it's a community favorite for creative freedom.

[Hugging Models @HuggingModels]

Face swap just got a massive upgrade. BFS Best Face Swap is a LoRA for Qwen Image that swaps faces, heads, and even bodies in one shot. 219k downloads and counting. Here's why it's blowing up.

[Google DeepMind @GoogleDeepMind]

Meet EmbeddingGemma 2, our first natively multimodal open model for on-device embeddings.

It expands beyond text to unify code, images, audio, and video in a shared space. 🧵

[Hugging Models @HuggingModels]

New AI model alert! MiniMax-H3-X2-Detail-VAE is here to supercharge your image-to-video game. It's a specialized VAE for ComfyUI that adds insane detail and x2 upscaling. Perfect for creators who want crisp, high-res videos from a single reference image.

[Hugging Models @HuggingModels]

Check out DeepSeek-V4.1-MLX-Q4i.

[merve @mervenoyann]

btw if you want to learn to train models to be agents, we have a four chapter series on youtube with everything open-source 🙌🏻

get started here https://t.co/56TVr9FSBm

[ComfyUI @ComfyUI]

Ideogram 4.5 is now in ComfyUI.

It's an edit model built to fix drift. 4.5 keeps the rest of your image intact, edit after edit.

→ Multi-turn edits that stay clean
→ Edit 24MP+ images without downscaling, with crop edges preserved so the edit stitches back in seamlessly
→ Translate text in signage, packaging, and banners
→ Style reference, sketch-to-image, depth-to-image, and photo restoration

Click the link below to run the workflows ⬇️

[Hugging Models @HuggingModels]

Meet Qwen3.8-27B: a multimodal powerhouse that reads images AND text, then talks back. 7 million downloads and 16k likes say this model is doing something right. Here's why devs are obsessed.

[Hugging Models @HuggingModels]

Meet TeleOCR, a multimodal AI that turns images of text into clean, structured data. With 27k+ downloads, it's a hit for OCR and document parsing. Built on Qwen2.5-VL, it's your go-to for extracting text from images.

[Hugging Models @HuggingModels]

Text to image just got a serious upgrade. Qwen-Image-2.1-Fix is a LoRA adapter that supercharges the Qwen-Image-2.1 base model. Think sharper details, better prompts, cleaner outputs. The community is already buzzing with nearly 5k downloads.

[Hugging Models @HuggingModels]

What if you could swap any character in a video with AI? MiniMax-H3-Character-Swap-LoRA does exactly that. It's a video-to-video diffusion model that edits characters in existing footage. Game changer for creators.

[Stable Diffusion online AI @ai_diffusion]

🐱 🍣