Introducing Kontext Relight! 💡 ✨ A FLUX Kontext Relight... LoRA + demo trained for state-of-the art relighting for subjects & landscapesshow more

Fun workflow I was playing with last night 1)... Kontext to remove Thor from the shot 2) Photopea to place Shrek 3) Kontext + Relight lora to blend him into the shot 4) Wan2.2 i2V to animate Very addicting... 😍 Prompts are written up in the corner. Wan 2.2 prompt below 👇show more

🧮Turn single image into a custom LoRA model in... one click ! Should work for character and product ! This ComfyUI workflow: → Uses Gemini AI to generate 20 diverse prompts from your image → Creates 20 consistent variations with FLUX.1 Kontext → Automatically builds the dataset + trains the LoRA One image in → Trained LoRA out 🎯 #ComfyUI #LoRA #AIArt #FLUX #AutomatedAI ComfyUI Black Forest Labs 🔗 Check it out: This workflow was made for the hackathon organized by ComfyUI in SF yesterdayshow more

.Beeble released a new feature for SwitchLight, allowing you... to relight videos dynamically. Video by Skyglass Check it out: #AI #relighting #lighting #gamedev #photoediting #gamedevelopmentshow more

Flux Kontext is easily one of the best image... editing models out there, but it’s capable of so much more. A quick test: creating a product shot using only Flux Kontext. This was done with just one reference image and a few prompts to generate different angles.show more

Slopfactory open for business 🧌. Created using WAN 2.1... + Flux Kontext + Flux Fill + ComfyUI Workflow and breakdown to follow. Known issues: Lipsync could be better I could have composited the original woman back Start to finish ~1.5hrs of workshow more

this LoRA is awesome for portraits with z image!... love the aesthetic & details built a demo for it 👇✨show more

Freepik releases two insane features for character consistency. You... can now edit images using FLUX Kontext, and generate hyper-realistic AI videos with the new Kling 2.1. Here’s the full workflow:show more

Testing this Nunchaku implementation for ComfyUI Flux Kontext [dev]... on a 4090 GPU Actually lighting fast.... from a fully cold start to finished render it took 13s.... That includes loading all of the models, clips, vae. Very impressive.. link belowshow more

Yesss Jasper introduces LBM: Latent Bridge Matching for Fast... Image-to-Image Translation💡 and drops an amazing ✨image relighting✨ demo that runs with a single(!) inference step 🔥show more

🧵✨ Kontext Thread Challenge 🧵✨ This month, we’re planning... a special challenge with TZ APAC! We want to see how far you can take Flux.1 Kontext for transformations. Not just character consistency, but style, mood, and/or story evolution and make a thread about your creative process! Mission: Pick 1 base character or portrait → use Kontext to transform it across 4 different vibes. Some examples: 🔸Normal → Cyberpunk → Fantasy Armor → Pixar-style 🔸Morning → Golden Hour → Neon Night → Black-and-white Film Noir 🔸Casual Outfit → Royal Costume → Spacesuit → Streetwear 🔸Or add/remove things from your initial pictures that give 4 different results Here’s how to enter: 1️⃣ Start your thread with your base/reference image. 2️⃣ Post each new render as a reply. 3️⃣ Explain your steps (prompt choices, edits, tweaks). 4️⃣ Finish with a collage/carousel of all 4 images together. To qualify, make sure to: ✅ Use to create ✅ Use only Flux.1 Kontext ✅ Add your prompt settings in each post ✅ Include the mention "Flux.1 Kontext on Sogni" in your first tweet ✅ Mention your Sogni username ✅Tag Sogni.ai, TZ APAC & Tezos on your pictures 🏆 Prizes 5 winners will share: ✨ 25,000 Premium Sparks ✨ $500 in SOGNI tokens ✨ $500 in tez (XTZ) ℹ️ Winning threads may also be featured across Sogni platforms (with full credit to you). 📅Deadline: Oct 3 (1PM UTC)show more

FLUX Kontext is now part of Firefly Boards along... with other models 🎉 You can edit your photos with text. Great use case is photo restoration! I felt incredible seeing my Grandmothers' photos in color. Btw, Firefly Boards is available for everyone to use now. Enjoy!show more

I've been working on my first upscaling/detail enhancer LoRA,... trained on Flux Klein 9B, which is something I've been wanting to try out for a while. Still needs more training, but so far so goodshow more

WOW this is a game changer for concert visuals!!... Using Beeble 's SwitchX model I was able to relight the same video to create 8 different light passes and then edit this together in Premiere! 🤯 Thanks Jules Urbach for the suggestion!show more

i made a state-of-the-art-for-1980 speech synth just for laughs

Today we are releasing FLUX.1 Krea [dev] - a... new state-of-the-art open-weights FLUX model, built for photorealism. Developed in collaboration with Krea, this model is focused on images with unique aesthetics. No “AI look”, no blown-out highlights, just natural detail.show more

A little experiment I wanted to try with Wan... Vase, Flux.1 Kontext, and Act 1. ❗️Disclaimer: Posting this is not me saying it would be better in color, that it should be made in color, or that this would be suitable for final production use. I just wanted to test what’s possible. 😊show more

I just built a demo for this Light Migration... LoRA on Hugging Face the quality surprises me on every output 🤯show more

Introducing our new family of state-of-the-art AI models: Phoenix-3,... Raven-0, and Sparrow-0. Together they bring Conversational Video Interfaces (CVI) to the next level, and power Charlie, our new demo persona 👋show more

Okay last one Let's try a painting "Fall of... New Amsterdam", a painting from 1932 about the 1664 fall of New Amsterdam to the British First turned into a photo with Flux Kontext Then turned into a video with Kling 2.1 and added audio with Elevenlabs, obviously it needs some actual 1664 Dutch shouting And the video isn't without anomalies But nice to see what's possible nowshow more

✨Contributor Spotlights✨ Introducing one of our amazing Page Artists... for A Happy Zine in Hell, ✖️ƬIΛ➕ ! Here to bring all their talent to make some amazing art!!✨show more