ComfyUI Node
🎲 LDM Sampler
Runs the diffusion sampling loop to denoise the latent. Samplers (alpha-space, native to the LDM paper): • ddim — deterministic DDIM (eta controls stochasticity: 0=det, 1≈ddpm); • ddpm — ancestral DDPM (always stochastic); • plms — pseudo-linear multistep. Compatible schedulers: ddim_uniform, linear, beta. Samplers (sigma-space, k-diffusion family): • euler / euler_ancestral / heun / dpmpp_2m. Compatible schedulers: all (ddim_uniform, linear, beta, karras, exponential, cosine). denoise=1.0 generates from pure noise (txt2img). Values < 1.0 partially denoise an existing latent (img2img). NOTE: This model was trained without classifier-free guidance. There is no negative prompt and no CFG scale.
🎲 LDM Sampler
- model
- positive
- latent_image
- LATENT
◄seed42►
◄steps50►
◄sampler_name▾►
◄scheduler▾►
◄eta0.00►
◄denoise1.00►
CategoryLDM
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| model | LDM_MODEL | MODEL output from Load LDM Checkpoint. | |
| positive | LDM_CONDITIONING | CONDITIONING from BERT Text Encode node. | |
| latent_image | LDM_LATENT | Starting latent: empty (txt2img) or encoded image (img2img). | |
| seed | INT | 420–18446744073709550000 | Random seed for initial noise. |
| steps | INT | 501–1000 | Number of denoising steps. k-diffusion samplers converge well at 20–30 steps. |
| sampler_name | COMBO | ddim/ddpm/plms are alpha-space (LDM paper native). euler/heun/dpmpp_2m are sigma-space (k-diffusion). | |
| scheduler | COMBO | Sigma schedule. Alpha-space samplers (ddim/ddpm/plms) accept: ddim_uniform, linear, beta. Sigma-space samplers accept all schedulers. | |
| eta | FLOAT | 0.000–1 | Stochasticity for DDIM only. 0 = deterministic, 1 ≈ DDPM. Ignored by other samplers. |
| denoise | FLOAT | 1.000–1 | 1.0 = full generation from noise; < 1.0 = partial denoising (img2img). |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| LATENT | LDM_LATENT | — |