logo
RunComfy
  • ComfyUI
  • TrainerNew
  • Models
  • API
  • Pricing
discord logo
MODELS
Explore
All Models
LIBRARY
Generations
MODEL APIS
API Docs
API Keys
ACCOUNT
Usage

FLUX 3 Draft First Last Frame to Video: Fast Start-End Drafts on Models and API | RunComfy

blackforestlabs/flux-3/first-last-frame-to-video/draft

FLUX 3 Draft First Last Frame to Video builds a fast 720p draft between start and end stills, with a reusable cache for later enhancement.

URL or data URI of the image used as the first frame of the draft.
URL or data URI of the image used as the last frame of the draft.
The text prompt describing the draft video.
Aspect ratio of the generated draft. auto lets the model choose.
Draft duration in whole seconds from 5 through 20.
Whether to generate audio for the draft video.
The safety tolerance level for the generated video. 0 is the strictest and 4 is the most permissive.
Idle
The rate is $0.06 per second of generated draft video (720p).

Introduction To FLUX 3 Draft First Last Frame to Video

Black Forest Labs' FLUX 3 Draft First Last Frame to Video bridges a start still and an end still into a fast 720p clip from a written brief, built for cheap transition trials before a full-quality pass. Trading costly final-quality reruns for quicker bookend tests while keeping a reusable draft cache for later enhancement, FLUX 3 Draft First Last Frame to Video helps marketers, product teams, and previz artists iterate without burning budget. For developers, FLUX 3 Draft First Last Frame to Video on RunComfy can be used both in the browser and via an HTTP API, so you don't need to host or scale the model yourself.
Ideal for: Pose-to-Pose Drafts | Low-Cost Transition Tests | Scene Bridge Previews

Black Forest Labs / FLUX 3 Draft First Last Frame To Video#


This page covers the first-last-frame draft endpoint in the FLUX 3 family. You pin a start still and an end still, then describe the middle; the model returns a quick 720p clip so you can validate the transition without paying full FLUX 3 First Last Frame rates.


The endpoint is built for the early loop of creative work: bookend composition checks, middle-motion tests, and batch draft runs. When a take looks right, reuse the returned draft cache with draft-enhance for a fuller finish.

Related Models

kling-1-6/pro/text-to-video

Generate high quality videos from text prompts using Kling 1.6 Pro.

dreamina-3-0/pro/text-to-video

Turn text into detailed cinematic scenes with Dreamina 3.0 precision.

hailuo-02/pro/image-to-video

Animate an image into a smooth 6s video with Hailuo 02 Pro.

video-background-removal/green-screen

AI-driven tool for seamless object separation and smooth video compositing.

kling-2-6/pro/text-to-video

Create lifelike 1080p clips from text with synced audio and flexible ratios.

ltx-2/fast/image-to-video

Transform visuals into smooth 4K motion clips with sync audio and rapid rendering.

Frequently Asked Questions

What is FLUX 3 Draft First Last Frame to Video best used for?

FLUX 3 Draft First Last Frame to Video bridges a start still and an end still into a fast 720p preview. It fits pose-to-pose trials, product reveals, and cheap transition tests before a full-quality pass.

How does FLUX 3 Draft First Last Frame to Video differ from the full FLUX 3 first-last endpoint?

Both use start and end frames; FLUX 3 Draft First Last Frame to Video returns a cheaper 720p preview plus a draft cache, while the full endpoint is better for polished 720p or 1080p deliverables.

What inputs and duration does FLUX 3 Draft First Last Frame to Video support?

FLUX 3 Draft First Last Frame to Video requires a prompt, start image URL, and end image URL. Duration is an integer from 5 to 20 seconds (default 5). Aspect ratios include auto plus common film and social frames.

Why does FLUX 3 Draft First Last Frame to Video need an explicit duration?

An explicit duration pins where the end frame lands on the timeline. Without a fixed length, the bookend placement for FLUX 3 Draft First Last Frame to Video cannot be validated cleanly.

What is the draft cache from FLUX 3 Draft First Last Frame to Video?

Along with the preview clip, FLUX 3 Draft First Last Frame to Video returns a reusable draft cache you can pass to draft-enhance for a fuller-quality render.

Can developers call FLUX 3 Draft First Last Frame to Video through the RunComfy API?

Yes. Prototype in the RunComfy model UI, then call the same FLUX 3 Draft First Last Frame to Video template through the RunComfy API with matching parameters. Generations consume usd / credits on both paths.

How much does FLUX 3 Draft First Last Frame to Video cost on RunComfy?

FLUX 3 Draft First Last Frame to Video is billed at $0.06 per second of generated draft video at 720p. A 5-second clip costs about $0.30; longer durations scale with the output length.

When should I stay on FLUX 3 Draft First Last Frame to Video versus full quality?

Stay on FLUX 3 Draft First Last Frame to Video for bookend drafts and early transition reviews. Move to the full first-last endpoint or draft-enhance for sharper finals.

Follow us
  • LinkedIn
  • Facebook
  • Instagram
  • Twitter
Support
  • Discord
  • Email
  • System Status
  • Affiliate
Video Models
  • MiniMax H3
  • Minimax H3 Image to Video
  • FLUX 3 Video
  • Happy Horse 1.1 reference to video
  • Wan 2.6 Flash
  • Hailuo 2.3 Fast Standard
  • View All Models →
Image Models
  • FLUX 3 Image
  • Seedream 5.0 Pro Image Edit
  • Flux 2 Flash Edit
  • seedream 4.0
  • GPT Image 2 Image Edit
  • Nano Banana Pro
  • View All Models →
Legal
  • Terms of Service
  • Privacy Policy
  • Cookie Policy
RunComfy
Copyright 2026 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

Examples Of FLUX 3 Draft First Last Frame to Video

Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...