ComfyUI Node
Step Film
Recorded steps as video frames: each step's picture over a strip with a label, the step number and a progress bar, ending on the sampler's result. Wire a second recording into steps_b to play two runs beside each other on the same clock. Send the IMAGE to Create Video.
Step Film
- steps
- vae
- result
- steps_b
- result_b
- frames
◄label►
◄showprediction►
◄frames_per_step1►
◄hold24►
◄label_b►
◄layoutside by side►
CategoryNynxz/Diagnostics
Inputs (11)
| Name | Type | Default | Description |
|---|---|---|---|
| steps | NYNXZ_STEPS | From Record Steps. | |
| vae | VAE | — | |
| result | LATENT | The LATENT of the sampler that ran on Record Steps' model. It is the last frame, and it makes this node wait for that sampler. | |
| label | STRING | Written under this run. | |
| show | COMBO | prediction | prediction: the clean image the model expects at each step — how the picture forms. noisy: the latent the sampler actually holds, noise and all. |
| frames_per_step | INT | 11–30 | Frames each step stays on screen. With few steps, raise it instead of lowering the video's frame rate. |
| hold | INT | 240–240 | Extra frames the result stays on screen at the end. |
| steps_bopt | NYNXZ_STEPS | A second run to compare with. | |
| result_bopt | LATENT | The second run's sampler LATENT. | |
| label_bopt | STRING | — | |
| layoutopt | COMBO | side by side | 2 options: side by side, stacked |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| frames | IMAGE | — |