FLUX.3 Edit
FLUX.3 Edit is the video editing endpoint of Black Forest Labs FLUX.3. It re-renders an existing clip from a natural-language instruction, applying targeted changes while preserving motion, timing, and framing. Input videos should be MP4 under 50 MB and under 15 seconds; output follows the source clip at 720p. Built for iterating on existing footage without regenerating the whole shot. It is the cheap, fast pick for restyles and local edits that keep the source's shots, timing, and audio. New lettering comes out garbled and anything it adds stays static, so a subject that has to act belongs on MiniMax H3 Reference.
See more
FLUX.3 Edit is the video editing endpoint of Black Forest Labs FLUX.3. It re-renders an existing clip from a natural-language instruction, applying targeted changes while preserving motion, timing, and framing. Input videos should be MP4 under 50 MB and under 15 seconds; output follows the source clip at 720p. Built for iterating on existing footage without regenerating the whole shot. It is the cheap, fast pick for restyles and local edits that keep the source's shots, timing, and audio. New lettering comes out garbled and anything it adds stays static, so a subject that has to act belongs on MiniMax H3 Reference.
Connect Claude, Cursor, VS Code, or Codex to Layer’s MCP server and FLUX.3 Edit becomes a tool your agent can reach for — it picks the parameters, runs the generation, and shows you the result in the conversation.
https://mcp.app.layer.ai/mcpAsk your agent
“Use FLUX.3 Edit to animate a torch-lit dungeon corridor with a slow dolly forward.”
execute_forge({
"base_model_id": "flux-3-edit",
"prompt": "A torch-lit dungeon corridor, slow dolly forward",
"batch_size": 1
})Authenticate with a personal access token, post the model’s own form, and poll the inference until it completes. Every field below is accepted by this endpoint.
# Start the generation — returns an inference id straight away.
curl -X POST https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/base-models/bfl-flux-3-edit/inferences \
-H "Authorization: Bearer $LAYER_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"prompt": "A torch-lit dungeon corridor, slow dolly forward"
}'
# Poll until status is "complete" — the response then carries the asset URLs.
curl https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/inferences/$INFERENCE_ID \
-H "Authorization: Bearer $LAYER_TOKEN"- prompt stringrequired
- Describe what to generate, or the change to make.
- guidance_file_init_video file[]required
- The video to modify
- prompt_language string
- The language the prompt is written in, so it reaches the model as you meant it.
Why use FLUX.3 Edit for video?
Cinematic video generation
FLUX.3 Edit creates high-fidelity video content suitable for trailers, gameplay previews, and marketing materials with temporal consistency.
Flexible input modes
Generate from text prompts, reference images, or existing video. Supports various aspect ratios and durations for different content needs.
Production-ready output
Clean motion, stable framing, and coherent transitions make outputs ready for direct use in UA campaigns and social content.
Game trailers and cinematic previews
Create attention-grabbing trailers and gameplay previews that showcase your game at its best. High temporal consistency ensures smooth, professional results.
UA video creative at scale
Generate dozens of video ad variants for A/B testing across platforms. Rapid iteration lets performance teams optimize creative angles quickly.
Character animations and in-game cinematics
Bring characters to life with animated sequences for cutscenes, promotional materials, and social content.
FAQ
How much does FLUX.3 Edit cost? Is it free?+
How does Layer's pricing work?+
There are no seat fees, feature gates, or plans on Layer. Instead, our platform uses a consumption based system with Creative Units (CUs) with a flexible monthly subscription. Every generation on Layer (image, video, 3D, or audio) consumes a Creative Unit, and you only pay for what you create.
What Elo score does FLUX.3 Edit have?+
Other video models on Layer
FLUX.3 Extend
Black Forest Labs
Extend an existing video clip with FLUX.3, continuing motion and native audio from the source ending.
FLUX.3 Keyframes
Black Forest Labs
Guide FLUX.3 video generation with up to 10 keyframe images pinned across the clip.
FLUX.3
Black Forest Labs
Frontier video model from Black Forest Labs with native audio, lipsync, and first/last frame control.
Veo 2
Legacy video model generating high-definition, long-form cinematic video content.
Seedance 2.5 Reference
ByteDance
Reference-guided Seedance 2.5 video with up to 30 images, 10 videos, and 10 audio files.
Seedance 2.5
ByteDance
ByteDance's Seedance 2.5 video model with up to 30s clips, 480p/720p/1080p output, and native audio.