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

Here's a reference comparison for this shot from #KFP4.... Ping & Li were such fun characters to animate. Fun fact: The bunny wasn't originally in this shot. I came up with the idea with the awesome LIRON TOPAZ. No muppets were harmed in the making of this shot...show more

GPT Image 2 + Seedance 2.0 on mitte.ai When... using storyboards, I try not to describe every shot in the video prompt as much as possible. To support that, I started adding more details into the storyboards instead. The idea is letting the storyboard carry shot order, pacing, camera logic and continuity while keeping the video prompt simpler. Still experimenting with it but results feel promising. You can check the prompts and result.show more

GPT Image 2 + Seedance 2.0 - Prompt Share... Even though it doesn't come close to the effects in the anime Witch Hat Atelier, it was a major source of inspiration for this idea. This time, since the storyboard panels didn't include many scene-specific details, I described each shot directly in the prompt. You can check the prompts below.show more

This guy transforms into top OnlyFans models with one... click 6.4M views in 3 weeks. nobody can tell which face is real the workflow: -> Pinterest → 2 contrasting faces -> Nano Banana Pro → merge into one AI face -> Kling → transfer movement from a real reference video -> CapCut → remove the AI plastic look 30 minutes from zero to a viral AI girl the article below breaks down the exact prompts and settings 👇show more

I love samurai duel scenes To make them feel... more chaotic, immersive, and cinematic, handheld camera movement adds so much energy to the shot I created this one with Seedance in Magnific Prompt below 👇show more

I was delighted to animate these shots because fireballs... and lava FX are fun. Credits to Kai Asakawa for plussing the echo fx animation in the 2nd shot! Also congrats to the #gameoverse team for surpassing the 10 million mark so quickly :0 RubberRoss GLITCH StudioMealashow more

FUN FACT! This shot from the pilot was the... VERY last one that I animated! It was a LOT of fun since Casey, Cleaveland's VA, improvised most of his takes as to HOW they might bring the Ace of Wands back from the void. The Episode TWO Crowdfund is 52% funded with 20 days to go!show more

Kling 3.0 Tip — CINEMATIC MULTISHOT (Narrative Scenes) With... Kling AI 3.0's Multishot feature. We are making Short Films. These templates allow you to direct a continuous scene with 3-4 camera angles, dialogue, and emotional shifts. THE TECHNIQUE: "The 4-Shot Arc" Don't just describe a scene. Describe the cuts. Use Shot 1, Shot 2, Shot 3 labels to tell the AI exactly when to switch angles while keeping the characters consistent. N.B. ENABLE MULTISHOT OPTION ⚠️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

😈 While we are waiting for Seedance 2.0, Kling... 3.0 is still an amazing option. Especially Omni mode when working with character. Just generate multiple facial expressions and provide them as reference images. Then make a multi-shot prompt and you will have amazing character consistency. Prompt: shot 1: the devil talking while turning his head giving a side eye. shot 2: extreme close up of the devils eye. he winks. shot 3: extreme close up of the mouth while he turns agry. shot 4: extreme close up of his ear. small hairs are showing. shot 5. the devil sticks out his tongue while saying a licking sound shot 6: zoom out and show the devil standing in hell. Only a silhuette is visible. Link to Spaces belowshow more

I was given a very cool gun to animate... by Katja Linssen. Had fun coming up with different angles to show the different parts. It was also a good way to practice rendering in Unreal See below for Katja's portfolio. There's a lot of amazing hard-surface artwork!show more

Derrick White was THE INBOUNDER on this play! In... less than 3 seconds, he: 1) Inbounded the ball. 2) Spaced to the corner for a potential kick-back pass. 3) Read Smart's shot and crashed the glass. 4) Tipped in the game-winner. Just an absurd basketball IQ and high-effort play.show more

How I made the video below (17s): 1. Use... Nano Banana to generate keyframes (a consistent world + full environment) 2. Use Kling with first/last frame reference to generate the in-between shots (bring the keyframes to life) 3. Use CapCut for revisions and editing (pacing, transitions, SFX, subtitles) There are three main challenges: 1. Getting AI to produce story-driven visuals: you need to bake relationships and narrative intent into the prompt 2. Writing prompts in cinematic language: specify shot types, camera movement, and framing changes to make transitions smoother 3. Editing is the real “ceiling”: assembling shots, controlling rhythm, building emotion, and syncing sound with visuals all come down to editing Making AI shorts is basically a hybrid job: writer-director + editor. If you understand storytelling and camera grammar—and then cut it with the right rhythm—the results get dramatically better.show more

Behind the Scenes: How I prompted 3 scenes in... 1 try on Seedance 2.0! Sharing my workflow of all my prompts for hopeless steve so you can see what were SD2 choices and what needed to be prompted. You can see how much more streamlined it is to go from one scene to the next when you can have 9 ref img's to work with. The prompt is only for the one that generated the most useful footage for each part. Scene 1, 2, 3 - 15s Ref: 1. House Ext. 2, Steve profile 3. Steve on the computer in the bedroom 4. mother cooking in kitchen. (The references a numbered so you know what the prompt is refering to.) Prompt: American sitcom style cartoon about Steve【@图片2】. Must maintain 100% fidelity to the art style and all character traits. No background music. [0:00-0:02] Wide establishing shot of the exterior of the house【@图片1】. Camera slowly zooms but remains in the wide shot. [Cut: 0:02-0:03] Interior wide shot of steve looking bored at computer 【@图片3】. No dialogue. [Cut: 0:03-0:05] Over the shoulder shot from behind steve. We see his monitor as he plays solitaire. We hear subtle mouse clicks and sound of cards as he drags and places them into the collumns. [Cut: 0:05-0:07] Side profile of Steve continuing to play solitaire on the computer. [Cut: 0:07-0:09] 【@图片4】Extreme close up of the mother's spatula flipping an egg over in the pan. [Cut: 0:09-0:11] Medium shot 【@图片4】 as the mother calls frustratedly, "Steve, breakfast is ready." [Cut: 0:11-0:12] Extreme close up in 【@图片4】of the mother's hand as she turns the stove off. [Cut: 0:12-0:13] 【@图片4】Extreme close up of the mother narrowing her eyes disgruntled. [Cut: 0:13-0:15] 【@图片4】 Medium shot as mother walks out of left of frame. Stationary camera.show more

One of the coolest prompts! Prompt : The camera... rockets up from below, tearing past jagged cliff walls, then whips into a downward tilt to reveal the ocean below in full violent eruption, waves detonating against black rock. On the cliff edge stands a warrior woman, utterly fearless, gazing into the maelstrom as if daring it to rise higher. The shot continues in one fluid move: the camera arcs past her, spirals downward around the cliff in a tightening circle, then rises slightly into a final close, frontal reveal of her face, wind-whipped, calm, and burning with determination.show more