Keep the SKU identical across shots
One still, then I2V or R2V. Seedance 2.0 (69cr) or Fast R2V (25cr). Do not re-prompt the bottle.
6 min read
Seedance 2.0 Fast R2V is 25 credits
Seedance 2.0 Fast R2V is 25 credits, 720p, native audio, 4–15s. Full Seedance 2.0 is 69 credits at 1080p. Fast is the draft/ref row.
6 min read
Wan 2.7: pick T2V, I2V, or R2V
Wan 2.7 T2V and I2V are 15 credits; R2V is 18. Audio is null on these video rows. Need native audio? Use Wan 2.6 T2V, Seedance, or Veo.
6 min read
Veo reference-to-video vs I2V
Pick Veo R2V when the stills are the brief. Pick I2V when the plate is frame one. The stack is not a first frame.
8 min read
When to pick VEO 3.1 Reference to Video
VEO 3.1 Reference to Video is a catalog row with a specific job. Here is when it earns the credit spend and when to route elsewhere.
6 min read
6 reference-to-video rows that want a stack, not a sentence
Reference-to-video is files, not adjectives. Six published rows: Veo 3.1 R2V (8s, 64cr, native audio), Happy Horse 1.0 R2V (3–15s, 28cr), Seedance 2.0 Fast R2V (4–15s, 25cr, native audio), Wan 2.7 R2V (2–10s, 18cr), Kling O3 Standard R2V (3–15s, 56cr, native audio), Gemini Omni Video (4–10s, 9cr, also R2V).
7 min read
Pipeline sleeves match three refs in VEO 3.1 R2V at 64cr, 8s
pig-launchers already opened the trap door. Sleeve leftover is the split clamp around this pipe: VEO 3.1 reference-to-video is 8s, 64cr, native audio, up to 3 reference images. A generated wrap with a different bolt circle is a different repair.
6 min read
@-references in Seedance versus R2V endpoints
Seedance 2.x @-files are multimodal references in one generate. /models/*-reference-to-video is a dedicated R2V endpoint. Different APIs, same job family.
6 min read
Gemini Omni Video: the reference stack is the brief
Gemini Omni Video is reference-to-video. Upload the stills that must appear. Do not spend the whole budget because the slider goes that far.
5 min read
Happy Horse 1.0 reference video starts from a stack
Happy Horse 1.0 Reference to Video is reference-to-video. Upload the stills that must appear. Do not spend the whole budget because the slider goes that far.
5 min read
Kling O3 Standard reference to video: add stills
Kling O3 Standard Reference to Video is reference-to-video. Upload the stills that must appear. Do not spend the whole budget because the slider goes that far.
3 min read
Seedance 2.0 Fast Reference to Video: upload stills
Seedance 2.0 Fast Reference to Video is reference-to-video. Upload the stills that must appear. Do not spend the whole budget because the slider goes that far.
4 min read
Seedance 2.0: the stack is the brief (4s, 5s, 6s, 1080p, 69cr)
Seedance 2.0 is reference-to-video. Upload the stills that must appear. Do not spend the whole budget because the slider goes that far.
4 min read
Seedance 2.5's reference budget: when fifty slots matter
2.5 accepts far more multimodal references than 2.0. You only need that when identity and product must lock across a sequence.
6 min read
VEO 3.1 Reference to Video: the stack is the brief (8s, 64cr)
VEO 3.1 Reference to Video is reference-to-video. Upload the stills that must appear. Do not spend the whole budget because the slider goes that far.
4 min read
Wan 2.7 Reference to Video: the stack is the brief (2s, 3s, 4s, 1080p, 18cr)
Wan 2.7 Reference to Video is reference-to-video. Upload the stills that must appear. Do not spend the whole budget because the slider goes that far.
4 min read
Describe the camera or hand it a reference clip
Which camera moves survive as text, which get silently approximated, and what a motion-reference clip costs you in framing freedom. With a three-bucket rule.
8 min read
Dialogue coverage: two-shots and reverse angles
Two people talking needs four shots, not one. The coverage set, the eyeline rule that makes reverses cut together, and the reference discipline behind both.
9 min read
How many reference slots your shot actually needs
Single-image, three-slot and nine-slot reference models compared: which shots improve past three references, which just get slower, and a shot-type table.
9 min read
How to spend H3's nine reference slots
MiniMax H3 takes nine reference images, three videos and three audio clips. A working slot budget for a character-plus-product series, and what to drop first.
9 min read
Consistency Collapse: Diagnosing Drift Between Shots
'It doesn't look consistent' isn't one problem. It's four — identity, wardrobe, set and lighting — each with a different cause and a different fix.
8 min read
How to keep a product consistent in AI video
A label-fidelity workflow for AI product video: canonical reference angles, why text-faithful models matter, and the check that catches drift before publish.
8 min read
Reference Stacking: The New Consistency Meta in AI Video
Grok Imagine, MiniMax H3 and Seedance 2.5 now take stacks of reference files instead of one. How to build a brand kit and match it to the right endpoint.
8 min read
Seedance 2.5: What 30-Second Single-Pass Generation Changes
ByteDance's Seedance 2.5 generates 30 seconds of synced audio and video in one pass with up to 30 references. What's new, and how to fake it today.
8 min read
Related topics
Reference To VideoShort Form Video291AI Video Generator280Brand Video Marketing280Content Creation256Image To Video239Content Marketing193Social Media Strategy152Brand Growth114First Last Frame96Captions93Seedance 2 592Credits84AI Video83Text Overlay70Ideogram V469Vidu Q369Agent66Video Generation66Digital Marketing65Finishing64AI Advertising62Flux 362Video Editing60Text To Video59Instagram Reels57Native Audio55Viral Video Strategy55VEO 3.154AI Disclosure52AI UGC51Character Consistency51Business Video49Qwen Image 348Kling 3 Turbo47Voice Cloning47Product Video45Seedance43Text To Image42Text To Speech42Content Strategy41Free Tools41Workflows41Short Form40UGC Ads40Team Productivity39Image Editing37YouTube Shorts37AI Lipsync36Marketing Automation36Seedream 5 Pro36Video SEO35Voiceover35Likeness34TikTok Marketing34Post Production33Caption Styles32Image Generation32UGC32Ypp Health32Compliance31Minimax H331Faceless YouTube30Workflow30Wan 2.729Burned In Captions28Youtube28Sora 227Trending Videos27Accessibility26Prompting26Tiktok26API25Motion Control24Article 5023Client Contracts22Hailuo 2 3 Fast22Retention22AI Music21Auto Captions21Brand Consistency21Grok Imagine21Model Selection21Picture Lock21Prompt Engineering21Talking Head21Video Prompting21Youtube Monetization21Hooks20Luma Ray 220Timed Overlays20Agency Operations19AI For Creators19AI Music Generator19Audio Mixing19Continuity19Model Routing19Suno19Usage Rights19Disclosure18Ideogram18Kling Motion Control18Agent Jobs17AI Content Pipeline17AI Video Workflows17Aspect Ratio17Brand Kit17C2pa17Camera Control17Creative Testing17Creator Economy17Eu AI Act17Imagen 417Kling 3.017Kling O117Reference Images17Typography17Veo171080p16AI Video Pricing16Nano Banana 216Quality Control16Recreate16Seasonal Content16Talking Head Video16Audience Retention15Color Grading15Content Credentials15Edit Video15Hook Pack15Kling15Likeness Rights15Sound Design15TTS15Wcag15Ypp15AI Content Workflow14AI Dubbing14AI Voiceover14Automation14Dubbing14Frame Rate14Inpainting14Localization14MCP14Temporal Consistency14AI Content Label13AI Video Editing13Analytics13Brand Safety13Content Repurposing13Copyright13Explainer Video13Instagram13Versely Agent13AI Disclosure Rules12B Roll12Background Removal12Bytedance12Cinematic AI Video12Pricing12Product Photography12Production Workflow12Prompt Adherence12Recraft V412Safe Area12Slideshow12Stills12Synthetic Media12Thumbnails12Upscaling12Vertical Video12Youtube Policy12