Seedance 2.5 Draft gives you the same generation quality as Seedance 2.5, with a lower-resolution way to try out your ideas and save credits. Generate at 480p to test your prompt, review the scene, and refine the result while using fewer credits than higher-resolution generation.
Once you get a result you like, upscale that draft to 1080p within 7 days of generating it. Use 480p trials to find the right action, framing, and camera movement, then spend credits on higher resolution for the result you want to keep.
1. Seedance 2.5 Draft Strengths
| Strength | Application |
|---|---|
| Seedance 2.5 generation quality | Explore your scene with the quality of Seedance 2.5 while testing at a lower resolution. |
| Lower credit use for 480p trials | Try different prompts, actions, and camera directions while spending fewer credits than on higher-resolution generations. |
| Upscale only a good result | Review and refine your drafts, then choose the clip worth taking to 1080p. |
| 1080p upscale within 7 days | Upscale your chosen draft within 7 days of generating it. |
The draft stage helps you decide which result is worth upscaling. Check the scene at 480p, make targeted changes if needed, and move to 1080p once you are satisfied.
2. Choose a Mode and Inputs
Choose the mode in the Video Generation composer based on what should guide the clip:
| Mode | Use it when | What to provide |
|---|---|---|
| [Text] | You want to create a scene from a written description. | A focused prompt describing the subject, action, setting, and desired shot. |
| [Image References] | A still image should guide the appearance, composition, or subject. | Relevant images, plus instructions for what to preserve and what should move. |
| [Frames] | The opening composition, ending composition, or transition between them matters. | A required first frame, an optional last frame, and a prompt describing the change between them. |
| [Omni References] | Multiple media types should guide the same generation. | Image, character, video, or audio references, with each one's role explained in the prompt. |
For more about the Video Generation node and how to connect it in a workflow, see Video Generation. To make a sequence of planned scenes, you can prepare a visual plan with the Image Storyboard guide.
For a ready-to-use product campaign path, explore CawCut Ad Video and its step-by-step creation guide.
3. Prepare Inputs and References
Both the prompt and references work best when each has a clear job and does not conflict with the others. Before running the node:
- State the subject and one main action first, then add the setting, visual style, camera direction, and timing that matter to the shot.
- Keep the sequence focused. If the clip has multiple beats, describe them in order and make sure they can fit the selected duration.
- Describe observable results rather than vague qualities; for example, specify “slow camera push-in” instead of only “cinematic.”
- Use compatible directions. Avoid asking for a locked camera and a rapid tracking move in the same shot, or for several unrelated actions at once.
- Use a clear image or clip where the subject and important details are visible.
- Tell the model which reference guides the character, product, setting, style, motion, framing, or audio, and what each reference should contribute.
- Describe what should stay consistent, such as clothing, colors, object shape, or location.
- For a motion or video reference, name the action or camera behavior to use. Explain whether other visual details should come from a different reference.
- For an audio reference, say whether it should guide speech, rhythm, timing, or general sound.
- Keep only references that contribute to the shot. Similar or contradictory assets can make it less clear which detail to follow.
In Omni References mode, add image, character, video, and audio references to guide different parts of the scene. You can also connect compatible upstream nodes. For node connections, see Understanding Nodes. For character-specific reference sheets, see Keep Characters Consistent in AI-Generated Videos; for location layout and shot-to-shot continuity, see Keep Scenes Consistent With Storyboards.
4. CawCut Workflow and Settings
- Open a workflow and add a [Video Generation] node, or select one already on the canvas.
- Choose [Text], [Image References], [Frames], or [Omni References], based on the inputs you need.
- Select Seedance 2.5 Draft from the model menu.
- Add images, character references, video, or audio for the selected mode, and connect compatible upstream nodes where useful. Add the prompt in the composer or connect a text input.
- Review duration, aspect ratio, audio, and the other settings for the selected mode. Use 480p to test your prompt with fewer credits before choosing a result to upscale. Check the credit estimate if the node displays one; Credits explains CawCut credits.
- Run the node and preview the 480p draft. Check the subject, movement, framing, scene transitions, timing, sound, and important reference details.
- If the result needs changes, refine the prompt or references and generate another 480p draft. Keep testing at the lower resolution to save credits, and compare results until you find one you like.
- When you are satisfied, upscale the chosen draft to 1080p within 7 days of generating it. Review the 1080p output before downloading it or using it downstream.
The seven-day window applies to the draft you want to upscale. Review and choose your result in time to complete the upscale within that window.
To explore examples of connected creative pipelines, visit CawCut Workflow. If you prefer generating through an AI-agent chat, see the cawcut-generate skill guide.
5. Iterate and Troubleshoot
Keep prompt experiments at 480p to save credits while you check the creative direction. If the clip misses the intent, diagnose the largest mismatch and make a targeted change before choosing a draft to upscale:
| Issue | Try this |
|---|---|
| The subject looks different from the reference | Use a clearer reference, describe the distinguishing features, and remove other images that suggest a different appearance. |
| The action is unclear or incomplete | Reduce the prompt to one main action and make its order explicit. Avoid giving the subject several simultaneous tasks. |
| The camera moves in the wrong way | State one camera move and whether the subject, camera, or both should move. Remove conflicting framing instructions. |
| Several scenes feel disconnected | Simplify the sequence, identify the transition between beats, or split the idea into separate clips that you can assemble later. |
| Audio does not match the scene | Specify the intended speech, ambience, or music and its timing. Avoid combining incompatible audio directions. |
| Fine details are unstable | Use a larger, clearer reference, keep the shot less busy, and review the result at full size. Treat tiny labels and exact text as details to verify. |
When the scene works at 480p, upscale the chosen draft to 1080p within 7 days of generating it. Check fine details again in the 1080p output before using it.
Change one or two things per generation when possible. That makes it easier to tell whether the prompt, reference, mode, or setting improved the result. If you are building a larger workflow, connect the video output to the next compatible node rather than repeating earlier steps. To join generated clips or add transitions between them, see Video and Transition Nodes.