An experienced prompt engineer (promptologist) is required, well-versed in Google's graphic and multimodal models (Gemini, Nano Banana / Imagen 3) Key objective: Develop two universal, template-based prompts The prompts must work with any incoming photographs without the need to manually rewrite the text for each new case. The generation result must be crystal realistic, without visual artifacts of AI (“glossy” plastic skin, unnatural shine, blurred details). The photographs should look like frames from real life. Task essence in detail: The project consists of two phases, each requiring a ready universal prompt (with variables for API/n8n):Phase 1: Generation of variable “types” (70–80% similarity) Input: One original photo of a real person (any gender, nationality, age). Task: A universal prompt that takes the original photo and generates 10 new, different personalities of the same type. Requirements: Similarity 70–80%: The model should not completely copy the person but must strictly maintain race, nationality, eye color, skull shape, and distinctive features, position in the photo (if it’s just a person’s face, the generated photos should also be). Controllability: The prompt should allow adjusting the degree of similarity/variability (for example, by changing parameters or passing a variable value of similarity). Realism: Microtexture of skin, pores, natural irregularities, realistic lighting.Phase 2: Universal Inpainting / Face Swap Input: Original photo scene New face generated in Phase 1. Task: A universal prompt for replacing the face in the photo scene with the new face while preserving the environment. Requirements: Complete universality: The prompt must work correctly on any types of scenes (different lighting, angles, quality of the original) without manual adjustment of the text for each frame. Scene preservation: Changing the background, clothing, lighting, pose, or hairstyle of the original scene is prohibited. Only geometry and facial features are replaced. Seamlessness: The new face must automatically adjust to the lighting, shadow, and color of the target frame. No seams, blurs, or “mask” effects. The prompts must be formatted as dynamic templates with variables (parameters) that can be easily substituted via JSON/n8n HTTP Request node or standard integrations. The freelancer must provide detailed instructions on calling: which specific API parameters (temperature, top_p, guidance scale, style weight, etc.) ensure stable results during automatic runs. Requirements for the performer Deep experience with Gemini / Nano Banana API: Understanding how the model accepts multimodal references (Image-to-Image / Inpainting) via API. Portfolio: Availability of real examples of photorealistic generation of people. (Anime, 3D, and “glossy” AI portraits are not considered). Understanding of automation: Experience in composing prompts for pipelines (n8n, Make, Python scripts), where stability and universality of response are important. When responding, you must be ready for a test process, meaning you generate 2-3 similar faces, then perform a test face swap. If you can write stable universal prompts without AI artifacts — we look forward to your response! Start your message with the word “Banana” when responding
Create a male image based on the example. In brands. Beautiful stylish images. I will send examples of how it was done with girls. Now we need to implement a male character. We will need many such photos. It is important that they look like real photos. Please indicate the price for 10 photographs. If you are ready right away, send 1 test photo. Thank you.
We are looking for a specialist to create a professional English-language video review of a SaaS platform with an AI chatbot for websites and online stores. We will provide the product name, access to the platform, and detailed information to the selected contractor. About the Product The platform helps companies communicate with website visitors through online chat, an AI assistant, and automated scripts. Main features: creating a knowledge base based on website content; automated responses to visitor inquiries; searching, recommending, and comparing products; showing products directly in the chat; collecting contact information from potential customers; visual editor for automated scripts; transferring the dialogue to an operator; shared panel for team collaboration; integrations with e-commerce platforms; customizing the appearance of the chat widget. What Needs to Be Done The contractor must: Familiarize themselves with the platform. Identify its main advantages and practical use cases. Prepare an English script and agree on it with us. Record a demonstration of the platform's functionality. Add professional English voiceover. Perform editing with zooms, transitions, captions, and highlighting important elements. Add English subtitles and unobtrusive background music. Make up to two rounds of revisions. We will provide a demo account and explain any features that may raise questions. Video Requirements Language: English. Duration: approximately 3–5 minutes. Format: 16:9. Resolution: 1920×1080 or higher. Natural and clear English voiceover. Modern style suitable for a B2B SaaS product. English subtitles. Final file in MP4 format without watermarks. Use of AI voice — only after agreement. The presence of a host on screen is not mandatory. A quality screen recording with professional voiceover will suffice. Deliverables agreed English script; ready Full HD video; version with English subtitles; SRT subtitle file; video cover; source project files, if included in the proposal. What to Indicate in the Response Examples of reviews of SaaS products or software. Total cost of work. Deadline for completion. Whether the script and English voiceover are included in the cost. What type of voice is used: own, narrator, or AI. Number of rounds of revisions. Whether you are willing to familiarize yourself with the product before recording. Desired deadline: 5–10 days.
Need to develop a package of branded motion elements for a YouTube channel. We are looking for a Motion Designer (After Effects) to create a branded package of elements that will be used in podcasts, expert videos, webinars, and Shorts. It is necessary to create 10 elements: Logo sting (intro) — 1 design, 2 background versions. Unique Selling Proposition (USP) opener — 1 template + 4 text versions + clean version. YouTube outro — 1 version + clean. Speaker title card — 2 templates. Lower Thirds — 2 templates. Telegram banner — 1. Loop background — 2 versions. Transition — 1. Event frame — 1 template. Vertical adaptations for Shorts — 2 elements. What we provide: brand book; logo in vector; fonts and brand colors; photos and video materials; references; QR codes; link to Google Drive with all necessary materials. Workflow: Agree on static style frames (design of main elements). After approval, the animation of the entire package is performed. Includes 2 rounds of revisions. Work results: After Effects output files (.aep) with editable layers; MP4 (H.264) for full-screen elements; MOV ProRes 4444 with alpha channel for overlays; clean versions according to the specifications; used fonts/assets and a brief instruction for text replacement. A detailed specification with all technical requirements is attached as a separate file. Deadline: by 15.08.2026. Budget: we await your proposals. Important: this is a test project. We are looking for a motion designer for long-term collaboration. If the result meets expectations, we plan to regularly order similar works and other video projects. All necessary materials for work are provided: brand book, logo in vector, brand colors and fonts, photos, videos, references, screencasts, and other brand materials — via the link to Google Drive: https://drive.google.com/drive/folders/1gZMQEaZSw4iIdICOD6SNNZcTd4KvgPRD?usp=drive_link
I'm looking for a specialist to complete a test task for generating sequential video content (pipeline: frame generation → editing in a graphic editor → Image-to-Video). A short test fragment needs to be implemented according to the provided script and prompts. Work stages within the test order: Generation of basic key frames in the specified style (preference is given to local running of Flux2 9bKlain and Wan2.1 14B Q8 / ComfyUI models). Basic correction/Inpainting of keys in a photo editor (Krita / Photoshop) to maintain frame consistency. Generation of intermediate I2V clips and transfer of output materials. Requirements for the performer: Powerful hardware for local generation (GPU from 12–24 GB VRAM) or the ability to work effectively with similar local builds. Basic skills in graphic editors (Krita / Photoshop). Understanding the principles of character and location consistency in AI generation. What I provide: A ready-made technical task, script, and working workflow. If you have the necessary hardware and understanding of the basics, but lack experience with a specific model — I will provide guidance and setup of the pipeline during the execution of the order. Payment and scope: Fixed payment for successfully completed test task (1 test scene / set of frames). Based on the quality of execution, we will discuss further individual tasks and expansion of cooperation in project form. The theme of time-lapse aging is presented as an example, but it can be different.
Need generation in AI or editing based on a video example of 10-15 seconds. About a chess academy, there is a sample. Well-generated AI options are accepted. Maybe someone has GEMINI PRO or other models.
I need help creating a realistic AI character for a series of videos about household appliances. I am looking for a specialist who can not only advise on the best approach and tools but also assist in setting up the entire process: character creation, video generation, voiceover, and a system so that in the future I can independently create new videos with this character. I am open to your recommendations and suggestions for the optimal solution.
I'm looking for a specialist with experience in video editing and creating ads with AI. We have a dozen 30-60 second promotional videos that need to have the product packaging replaced with ours, or change a few words in the voiceover and captions, or replace scenes with the website. All videos are in English. Budget is negotiable.
Technical specification for the video https://docs.google.com/document/d/12w1t4k1zskQxKpyy88I9w-H_roVMJD-3Ul7zCIcEljU/edit?usp=sharing
ContextWe are an escape room (Blackout-Room, https://blackout-room.com/), the universe of Le Sorcier Maudit — inspired by the Harry Potter universe (without direct elements from the movie).A few years ago, we ordered a promotional video for this universe (classic editing based on professional photos, simple effects: glow on the wand, igniting torch, light parallax). We really like this video, it worked well — but it has become too familiar to our audience over the years of showing. We want to not remake it from scratch, but improve and create a more advanced version in the same spirit, using modern AI tools.Video (reference): https://www.youtube.com/watch?v=DSy6YgB_gdQ Project GoalTo create a more advanced version of this promotional video (dynamic, atmospheric, for advertising on AdWords/Instagram/Facebook), using modern video generation/animation tools based on AI, to go much further than simple static effects: to bring photos to life into a full video scene (a wizard casting a spell on another, smoke, a character moving in the scenery, etc.) based on our existing photos. Required Result — First StageOne video for the universe "Le Sorcier Maudit", in 2 formats: Square 1:1 (1080x1080) Vertical 9:16 (Stories/Reels)Short duration (~25 seconds). MP4/MOV, H.264, audio stereo AAC 128kbps+.Additionally, we need a version of the video without text (clean editing/animation, without overlaid captions). This will allow us to independently test different text options and different "hooks" (beginning of the video) over the finished edited video.Important: this is a test stage. If the work is done well, we will order another 5 videos in the same format (2 options: vertical + square each) — meaning the project has the potential for a full long-term collaboration. What We ProvideA ready storyboard (attached) — a detailed plan by scenes with text, visuals, and type of animation for each frame, as well as our stock set of high-resolution photos (attached, only current project photos — without backup options). We will also provide the logo in vector format and brand book. What Style We Are Looking For Smooth, well-developed transitions between scenes (without abrupt cuts) Animation of decor/character elements, not just Ken Burns / basic parallax Compliance with the brand's visual identity Rhythm decreasing: the first scene is calmer to read the text, the following scenes are shorter What We Expect from the Performer Proficiency in one or more modern AI video generation/animation tools (image-to-video, motion, etc.) Classic editing skills (transitions, typography, sound design, export according to specified characteristics) Portfolio with examples of AI animation on static images (not just classic editing) Ability to quickly make edits based on feedback (in ticket format: one brief per video, edits collected in one place) Budget / TimelineTo be discussed — please indicate the price and estimated delivery time for this first video (considering the storyboard in the attachment, including the version without text). How to RespondPlease, before responding, carefully study the storyboard and photos attached to this project — all scenes, texts, visuals, and types of animation for each frame are detailed there. This will help you give an accurate estimate of cost and timelines, rather than an approximate one.After reviewing, please send: Portfolio (preferably with an example of AI animation based on a static photo) AI tools you usually use Cost and timeline estimate for this video
Need to create a video using AI, I will send an example. A bit with different sequences and voiceovers in various formats for advertising on social networks. Make it lightweight for easy loading. Voiceover in Ukrainian https://www.instagram.com/reel/DZ6T8xdPV9R/?igsh=MmMyeDB0cmh1eXh4
Project Description to create a camera path recreation. That is: same camera height; same focal length; same speed; same rotations; same FOV. Options for how this can be done: Option 1. AI Camera Match (best) ⭐⭐⭐⭐⭐ There are models that can analyze the movement of the first camera and generate or adapt the second video so that the camera moves almost identically. This is done through: Runway Gen-4 Google Flow (Veo) Luma AI Dream Machine Kling AI 2.1 The essence is: “Here is the video BEFORE the repair. Here is the video AFTER the repair. Make the camera of the second video the same as in the first.” This already works, although sometimes it requires several iterations. Option 2. Optical Flow + Warp ⭐⭐⭐⭐☆ If the difference is small, the editor can use AI in DaVinci Resolve or After Effects. AI: stabilizes; slightly changes perspective; adjusts speed; creates a smooth morph between frames. This is much cheaper. Option 3. Image-to-Video ⭐⭐⭐⭐⭐ If there are many photos or good video after the repair, AI can almost “fly” the camera through the room again. This is already being done by: Veo Kling Hailuo Luma Then it doesn't matter how the operator filmed at all.
I am looking for an experienced video editor to create a professional comeback video for my GTA YouTube channel, Absolute Gamer HD: The channel has around 13,000 subscribers and was previously focused on GTA 5 Online content, including glitches, tricks, modded outfits and tutorials. I have not uploaded for approximately nine years, and I now want to reactivate the channel in preparation for GTA 6. The first video will announce the return of the channel and should include: A powerful cinematic GTA-style comeback intro A short presentation of the channel’s history The transition from the GTA 5 era to GTA 6 A giveaway announcement for two GTA 6 copies A clear explanation of how viewers can participate An introduction to the content that will be posted from now on A teaser for the next video A professional branded outro The intro is very important. I want something dramatic and cinematic, not a basic logo animation or ready-made template. It should begin with a dark and nostalgic GTA 5 atmosphere, show that the channel has been inactive for nine years, and then transition into an energetic GTA 6 reveal. The video should include professional: Sound design Motion graphics Animated typography Music synchronization Speed ramps Glitch and cinematic effects Colour grading Clean transitions High-quality GTA 5 and GTA 6 footage I can provide: Links to my previous YouTube videos Channel screenshots and old footage The selected YouTube thumbnail Giveaway graphics GTA 6 footage and official Rockstar media links The general script, structure and creative direction The editor should be able to improve the concept creatively and turn the provided materials into a polished, engaging YouTube video. The expected full video length is approximately 3–5 minutes, including a cinematic intro of around 45–60 seconds. Experience with GTA videos, gaming trailers, YouTube content, Premiere Pro, After Effects, DaVinci Resolve or similar professional software is preferred. I am also interested in finding an editor for long-term collaboration. If the first project is completed successfully and the quality is good, I would like to continue working together on future GTA 5 and GTA 6 videos for the channel.