Nodes/comfyui-budgetpixel/SeeDance 2.0 Mini (BudgetPixel)
ComfyUI Node

SeeDance 2.0 Mini (BudgetPixel)

SeeDance 2.0 Mini — the cost-performance pick of the Seedance line

By budgetpixel-ai·Created about 17 hours ago·Updated about 12 hours ago· 3
SeeDance 2.0 Mini (BudgetPixel)
  • audio
  • end_image
  • image
  • reference_images
  • video
  • video
prompt
aspect_ratio16:9
generate_audiofalse
length_seconds5
resolution720p
force_rerunfalse

SeeDance 2.0 Mini is the one to build your default video workflow around. It has the same four modes as full SeeDance 2.0 - text, image, reference, video-edit - at 120 credits per second, the lowest per-second rate in the Seedance family and the "best cost-performance" tier ByteDance positions it as. The catch is the same as Fast: output tops out at 720p. If you're producing clips for screens, comps, or anything that won't be projected, Mini is the rational default and the full model is the splurge.

How it slots in

Between Fast (160 credits/sec, 720p) and the full model (220 credits/sec, up to 4K), Mini is the cheapest per-second Seedance 2.0 there is. Same mode mechanics, same input rules: image/end_image can't combine with reference_images or video, and audio reference needs an image or video alongside it. The one thing worth double-checking before you commit a run is resolution - 480p/720p only, so if the deliverable is 1080p, this is the wrong node and you want the standard 2.0.

The inputs that matter

  • prompt - required; edit instruction when video is connected.
  • image / end_image - start and optional end frame.
  • reference_images - up to 9.
  • video - the input clip for video-edit mode (2–15s, ≤100MB); bills input duration at half the output rate on top of the output.
  • length_seconds - 4–15.
  • resolution - 480p or 720p.
  • generate_audio - off by default.

Output is video (VIDEO) - 2025+ ComfyUI required for the core video type.

How it works

The standard pack pattern: serialized media to the hosted API, job created, polled until done, MP4 downloaded into the temp folder. Video jobs take minutes; the progress bar moving slowly is normal. Interrupting the graph stops the wait but a submitted job keeps rendering and billing server-side.

Install and key setup

ComfyUI Manager → BudgetPixel, or:

cd ComfyUI/custom_nodes
git clone https://github.com/budgetpixel-ai/comfyui-budgetpixel.git
pip install -r comfyui-budgetpixel/requirements.txt

Only requests. API key from a paid plan via BUDGETPIXEL_API_KEY or budgetpixel.json; keys never serialize into workflow JSON.

Where people get burned

The 720p ceiling is the whole gotcha - it's a real one for anyone whose output needs to be 1080p, so check the resolution dropdown before building the workflow. And remember the economics: per-second billing means a 15-second run costs 3× a 5-second run, and a video-edit bills input duration on top. force_rerun defeats ComfyUI's cache when you want a genuinely new take.

CategoryBudgetPixel/Video

Inputs (11)

NameTypeDefaultDescription
promptSTRINGText description of the video.
aspect_ratiooptCOMBO16:9Aspect ratio. Ignored when an input image or video already sets the frame.
audiooptAUDIOOptional reference audio (MP3/WAV/OGG) for the generated video. Provide a public audio URL or an uploaded-file URL from POST /v1/uploads (passed by URL, not inlined). Must accompany an image (`image` or `reference_images`) or a `video` input — audio can't be the only input.
end_imageoptIMAGEOptional end frame, used together with `image` (the start frame) to interpolate the video between the two frames. Same input forms as `image`.
generate_audiooptBOOLEANfalseGenerate audio with the video.
imageoptIMAGEOptional start frame for image-to-video. Provide a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. Omit for text-to-video.
length_secondsoptINT54–15Video length in seconds (4–15).
reference_imagesoptIMAGEOptional reference images that guide the generated video. Each item is a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. Can't be combined with `image`/`end_image` (start/end frames). Up to 9 on their own (reference-images-to-video); may also accompany a `video` to guide a video-edit, in which case up to 6 are used.
resolutionoptCOMBO720pOutput resolution. Pricing varies by resolution — see `resolution_pricing` in GET /v1/models.
videooptVIDEOOptional input video for video-to-video editing (2-15s, ≤100MB). Provide a public video URL or an uploaded-file URL from POST /v1/uploads (videos are passed by URL, not inlined). When set, the request runs in video-edit mode; you may also pass `reference_images` (up to 6) and/or an `audio` track to guide the edit. Not combinable with `image`/`end_image`. Billed on the INPUT duration at half the output per-second rate in addition to the output — estimate via POST /v1/cost.
force_rerunoptBOOLEANfalse

Outputs (1)

NameTypeDescription
videoVIDEO