Creating a fully immersive world happens with your color grading. Get the color grading shown in each setting by using the corresponding prompt keywords shown. Which is your favorite?

Introducing DaVinci Resolve 21.1! Major new update that introduces AI assistant integration, expanded support for still photography and camera formats, plus over 100 new tools and controls for faster editing and color grading workflows. Download now from

Cinema Studio 4 is now LIVE on Higgsfield. What's new: > 30+ new Camera Movement presets > 2-source Video Lighting Console > Color Grading with 50+ palettes > Acting Console with 6 emotions at 3 intensity levels > Video Extend with forward, bridge or backward generation > Scene-level edit inside a single generation > New asset management for collaborative work > New Сamera, Lens and Aperture options Direct your films, commercials and music videos with full production control in Cinema Studio 4, now on Higgsfield.

seedance prompt: Realistic Video Narration (15-Second Full Version - Pure First-Person POV): Presented in the style of unprocessed, handheld, unstable iPhone video footage. All camera settings are automatic, with no post-processing color grading or special effects. The footage captures the realistic breathing of the operator and slight, irregular hand shake. Autofocus frequently exhibits intense searching, brief out-of-focus periods, and delayed recovery. Auto white balance naturally shifts between warm and cool tones as it blends with the library lights and natural light from distant windows. The overall image is flat and slightly washed out, retaining realistic lens flare, edge purple-green iridescence, and slight overexposure or underexposure. Faint fingerprint artifacts occasionally appear at the bottom of the frame. Only natural ambient sound effects are used (the sound of turning pages, very light footsteps in the distance, the low hum of an air conditioner, suppressed breathing, and the subtle rustling of stockings against a cheongsam). All sounds are extremely suppressed, with slight microphone distortion at louder frequencies. The entire video employs a pure first-person POV perspective (student's subjective viewpoint), with camera movements completely following natural head rotations and gaze movements. The composition is occasionally imperfect, showing realistic breathing tremors and slight shaking during moments of tension. From 0-4 seconds, the camera, in a first-person perspective, rests on a desk in a secluded corner of the library, with noticeable breathing tremors. You can clearly see your legs in black trousers. A female teacher approaches from behind and sits directly opposite you, wearing a white, glossy cheongsam-style dress (high slit design, keyhole cutout at the chest, pink floral lace shoulder embellishments), paired with white suspender stockings and white garter belts. She suddenly leans forward, one hand reaching out to cover your mouth, the other pressing on the inside of your black trousers, whispering, "Don't make a sound... be good, sit still." Her voice is extremely low, yet carries a powerful seduction. The autofocus searches for the high slit of the white cheongsam and the white suspender stockings. Between 4 and 9 seconds, the teacher leans forward more proactively, the high slit of her glossy white cheongsam sliding upwards, revealing a large expanse of her fair thigh and white stockings. She whispers in your ear, "Watch closely... this is what you want to see." The camera instinctively lowers its focus, locking onto a close-up of your black trousers and the teacher's white stockings—the glossy cheongsam fabric taut, the stockings subtly reflective. Your breathing noticeably becomes heavier. Between 9 and 15 seconds, footsteps approach in the distance, and the teacher presses you down more aggressively, whispering a warning, "Someone's coming... but you can't move or make a sound." The high slit of the white cheongsam and the stockings are pressed tightly together, the image shakes violently, the tension reaching its peak. The footsteps grow closer, and the image freezes in an extremely oppressive atmosphere. The footage presents a realistic, unprocessed handheld video quality, a natural, imperfect feel reminiscent of a documentary, without any post-production color grading or special effects. All camera actions are consistent with the physical characteristics of iPhone automatic shooting.

Angel of the Gym, seedance prompt: Presented in the style of raw, handheld iPhone video footage, with all camera settings set to automatic, no post-processing color grading or special effects. The footage features slight hand-held shake and the operator's breathing sensation, occasional autofocus searching, delay, and brief loss of focus, automatic white balance switching between gym lighting and natural light. The image is flat overall, preserving real edge color fringing, slight overexposure, motion blur, and other optical imperfections. Only in-camera natural ambient sounds are used, including gym equipment sounds and faint air conditioning noise. Shot from a first-person handheld perspective, with natural reactive camera movements, occasionally slight swaying due to walking or adjusting angles. Medium and close-up compositions alternate, clearly showing the full body and action details of a plus-size Asian woman. Wearing the reference image of an elegant gold-embroidered long dress, she is exercising in the gym. She is wearing this formal dress, using cable machines and seated machines. At 0 seconds, the camera focuses on the woman from a medium shot, she is standing in front of the cable machine, hands gripping the handles ready to pull, the dress naturally flowing down. She slightly bows her head, quickly glancing at the camera with a hint of shyness. At 1 second, she starts pulling the cable with force, her body swaying back and forth, the sheer shoulder cape and skirt fluttering slightly with the movement. She frowns slightly as she exerts effort, occasionally looking up at the camera with a shy gaze. At 2 seconds, the woman continues pulling the machine, her movements accelerating, the dress fluttering with her body's sway. She looks up with a faint smile on her lips as she gazes at the camera. At 3 seconds, she stops pulling and walks to the nearby seated machine, sitting down, the dress swaying significantly with the movement. She lowers her head to adjust the hem and collar of the dress, her face showing a shy expression. At 4 seconds, she sits on the machine, leaning slightly forward, hands placed on her legs adjusting her posture. As she lowers her head to adjust her clothes, she looks at the camera with a shy gaze. At 5 seconds, she gently places her hands on her chest, slightly tilting her head up as she looks at the camera, a natural, slightly shy smile on her lips. At 6 seconds, she remains seated on the machine, looking at the camera with a soft gaze, a shy yet happy smile on her face, slightly adjusting her sitting posture. At 7 seconds, she stands up from the machine, the camera follows her movement, the dress fluttering slightly as she walks. She looks back at the camera with a shy and gentle smile. The footage presents a genuine, raw, handheld video quality with a documentary-level sense of natural imperfection, without any post-processing color grading or special effects. All camera behaviors conform to the physical characteristics of an iPhone being used in a gym.

Made with seedance 2.5 Prompt: Use @ Image1 as the visual baseline. Maintain a locked, static camera, a completely blurred muddy trench background with drifting smoke haze, floating embers, and the faint orange flicker of distant fires, and desaturated, gritty cinematic war-film color grading with heavy film grain. Ensure the paws remain strictly feline with no human fingers, and the helmet and rifle maintain rigid structural consistency without melting or warping. Execute this exact 15-second looped sequence: Start with only the very top curve of the green military helmet visible above the dirt mound. The white cat slowly rises vertically into frame, resting the miniature rifle on the dirt and taking aim. The cat squints its left eye tightly, grips the rifle with its right feline paw, and fires. The miniature rifle kicks back with sharp, rapid recoil, accompanied by a quick muzzle flash and a puff of smoke. An enemy round strikes the top of the dirt mound immediately after, blowing a spray of dirt into the air. The cat drops straight down behind the mound until it is completely hidden. While hidden, the cat lifts the helmet off its own head with both feline paws and balances it upside-down on the muzzle of the rifle. The cat's head is now bare, ears flattened. The cat slowly raises the rifle, and the helmet rises above the dirt line alone, wobbling gently as bait. The cat itself stays fully hidden behind the mound. The decoy helmet holds still above the dirt line. A long, deliberate pause. A rifle crack rings out and the helmet is knocked violently sideways off the barrel with a bright spark and a metallic ring, tumbling out of frame. In the same instant the cat pops up bare-headed, ears flat back, fur ruffled, eyes narrowed, shoulders the rifle and fires straight ahead. Sharp recoil, muzzle flash, and smoke. The cat holds the aim through the drifting smoke, then sinks slowly straight back down behind the dirt mound, catches the falling helmet, and sets it back on its head, ending exactly as the video started. Audio: a continuous low rumble of distant artillery, muffled shell impacts thudding at irregular intervals, fires crackling off-screen, a shell whistling overhead, and wind moving across open mud. Sharp dry rifle cracks on each shot, a bright metallic ping and ricochet whine when the decoy helmet is hit, and dirt pattering down after each impact. No music and no voices.

Episode 2: laundry day Prompt: "Comedic multi-shot sketch. Bouncy accordion comedy music throughout, natural sound and dialogue. All eight stylized 3D clay-render characters from the reference sheets appear together in every shot. SHOT 1 [00:00-00:07]: All eight at a laundromat, staring at one washing machine that is violently shaking. Beanie beard man: 'Did anyone read the label?' Hoodie beanie man slowly hides a bottle of soap behind his back. SHOT 2 [00:07-00:14]: Cut to the room filling with foam up to their chests. Leather cap man wades through, deadpan: 'This is fine.' Bucket hat dreads man is doing backstroke. Handheld, low angle. SHOT 3 [00:14-00:20]: Cut to all eight sitting outside on the sidewalk covered in foam, wearing each other's shrunken clothes. Beige cowboy hat man: 'Mine fits better now.' Wide shot, slow pull out. Stylized 3D animation, warm poster-like color grading, cinematic lighting, expressive comedic timing."

We hosted an intimate event on Agentic Engineering in SF with speakers at the forefront of AI yesterday. Three big lessons I took away: – @steipete: I now force contributors to OpenClaw to use a skill that pushes their prompt history of the code change to find signal in noise, to avoid often bad PRs that are 10,000 lines from a prompt “fix this” – @trq212: I used Claude to be a video editor to create a launch video with visuals, while having it interactively teach me about color grading as it did the edits. I didn't even know it could do that! Getting the most out of a model is finding your unknown unknowns. – @georgepickett: I spend a lot more human energy on crafting a plan upfront and getting all my clairfications answered upfront before leaving Codex to spin for days, armed with Ousterhout’s coding principles as a skill, on a well-crafted /goal We had about ~30 odd people including some recognizable names like Theo (@theo), Gergely (@GergelyOrosz), Andy (@andykonwinski), Jerry (@MillionInt), Dave Morin (@davemorin), Patrick Hsu (@pdhsu), Eric (@ericho), Bucky (@buckymoore), Joff (@mejoff) with a surprise visit from cricketer Robin Uthappa (@robbieuthappa) We were graciously hosted by @timshi_ai at his house and cohosted with @GregKamradt. Videos will be up soon! If you're interesting in coming to these, give me a shout in comments or in DM. (also incredible to see how huge the ClawFather is in the flesh)