API Reference
Parameters
curl --request POST \
--url https://api.daydream.live/beta/streams/{id}/prompts \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"params": {
"model_id": "stabilityai/sd-turbo",
"prompt": "<string>",
"prompt_interpolation_method": "linear",
"normalize_prompt_weights": true,
"normalize_seed_weights": true,
"negative_prompt": "<string>",
"guidance_scale": 123,
"delta": 123,
"num_inference_steps": 0,
"t_index_list": [
0
],
"use_safety_checker": true,
"width": 0,
"height": 0,
"lora_dict": {},
"use_lcm_lora": true,
"lcm_lora_id": "<string>",
"acceleration": "<string>",
"use_denoising_batch": true,
"do_add_noise": true,
"seed": 0,
"seed_interpolation_method": "linear",
"enable_similar_image_filter": true,
"similar_image_filter_threshold": 123,
"similar_image_filter_max_skip_frame": 0,
"controlnets": [
{
"model_id": "thibaud/controlnet-sd21-openpose-diffusers",
"conditioning_scale": 123,
"preprocessor": "<string>",
"enabled": true,
"preprocessor_params": {},
"control_guidance_start": 123,
"control_guidance_end": 123
}
],
"ip_adapter": {
"scale": 123,
"enabled": true,
"type": "regular",
"weight_type": "linear"
},
"ip_adapter_style_image_url": "<string>"
},
"pipeline": "live-video-to-video",
"model_id": "streamdiffusion"
}
'{
"success": true,
"message": "<string>",
"was_censored": true
}Submit StreamDiffusion Prompt (Deprecated)
Submit a prompt to a StreamDiffusion stream with advanced parameters including controlnets and lora settings
curl --request POST \
--url https://api.daydream.live/beta/streams/{id}/prompts \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"params": {
"model_id": "stabilityai/sd-turbo",
"prompt": "<string>",
"prompt_interpolation_method": "linear",
"normalize_prompt_weights": true,
"normalize_seed_weights": true,
"negative_prompt": "<string>",
"guidance_scale": 123,
"delta": 123,
"num_inference_steps": 0,
"t_index_list": [
0
],
"use_safety_checker": true,
"width": 0,
"height": 0,
"lora_dict": {},
"use_lcm_lora": true,
"lcm_lora_id": "<string>",
"acceleration": "<string>",
"use_denoising_batch": true,
"do_add_noise": true,
"seed": 0,
"seed_interpolation_method": "linear",
"enable_similar_image_filter": true,
"similar_image_filter_threshold": 123,
"similar_image_filter_max_skip_frame": 0,
"controlnets": [
{
"model_id": "thibaud/controlnet-sd21-openpose-diffusers",
"conditioning_scale": 123,
"preprocessor": "<string>",
"enabled": true,
"preprocessor_params": {},
"control_guidance_start": 123,
"control_guidance_end": 123
}
],
"ip_adapter": {
"scale": 123,
"enabled": true,
"type": "regular",
"weight_type": "linear"
},
"ip_adapter_style_image_url": "<string>"
},
"pipeline": "live-video-to-video",
"model_id": "streamdiffusion"
}
'{
"success": true,
"message": "<string>",
"was_censored": true
}prompt, guidance_scale, delta, num_inference_steps, t_index_list, seed, controlnets.conditioning_scale. All other parameters trigger a full pipeline reload (~30s).Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
Stream ID for stream diffusion processing
1Body
Show child attributes
Show child attributes
Base U-Net model to use for generation. Default: "stabilityai/sd-turbo"
stabilityai/sd-turbo, prompthero/openjourney-v4, Lykon/dreamshaper-8, stabilityai/sdxl-turbo Text prompt describing the desired image. Can be a single string or weighted list of (prompt, weight) tuples.
Method for interpolating between multiple prompts. Slerp provides smoother transitions than linear.
linear, slerp Whether to normalize prompt weights to sum to 1.0 for consistent generation.
Whether to normalize seed weights to sum to 1.0 for consistent generation.
Text describing what to avoid in the generated image.
Strength of prompt adherence. Higher values make the model follow the prompt more strictly.
Delta sets per-frame denoising progress: lower delta means steadier, less flicker but slower/softer; higher delta means faster, sharper but more flicker/artifacts (often reduce CFG).
Builds the full denoising schedule (the 'grid' of possible refinement steps). Changing it changes what each step number (t_index_list value) means. Keep it fixed for a session and only adjust if you're deliberately redefining the schedule; if you do, proportionally remap your t_index_list. Typical range 10–200 with default being 50.
-9007199254740991 <= x <= 9007199254740991The ordered list of step indices from the num_inference_steps schedule to execute per frame. Each index is one model pass, so latency scales with the list length. Higher indices (e.g., 40–49 on a 50-step grid) mainly polish and preserve structure (lower flicker), while lower indices (<20) rewrite structure (more flicker, creative). Values must be non-decreasing, and each between 0 and num_inference_steps.
⚠️ NOTE: t_index_list must have 1–4 elements, non-decreasing, and within [0, num_inference_steps]. The value should not go above 50.
-9007199254740991 <= x <= 9007199254740991Whether to use safety checker for content filtering
Output image width in pixels. Must be divisible by 64 and between 384-1024.
-9007199254740991 <= x <= 9007199254740991Output image height in pixels. Must be divisible by 64 and between 384-1024.
-9007199254740991 <= x <= 9007199254740991Dictionary mapping LoRA model paths to their weights for fine-tuning the base model.
Whether to use Latent Consistency Model LoRA for faster inference.
Identifier for the LCM LoRA model to use. Example: "latent-consistency/lcm-lora-sdv1-5"
Acceleration method for inference. Options: "none", "xformers", "tensorrt". TensorRT provides the best performance but requires engine compilation.
Whether to process multiple denoising steps in a single batch for efficiency.
Whether to add noise to input frames before processing. Enabling this slightly re-noises each frame to improve temporal stability, reduce ghosting/texture sticking, and prevent drift; disabling can yield sharper, lower-latency results but may increase flicker and artifact accumulation over time.
Random seed for generation. Can be a single integer or weighted list of (seed, weight) tuples.
-9007199254740991 <= x <= 9007199254740991Method for interpolating between multiple seeds. Slerp provides smoother transitions than linear.
linear, slerp Whether to skip frames that are too similar to the previous output to reduce flicker.
Similarity threshold for the image filter. Higher values allow more variation between frames.
Maximum number of consecutive frames that can be skipped by the similarity filter.
-9007199254740991 <= x <= 9007199254740991List of ControlNet configurations for guided generation. Each ControlNet provides different types of conditioning (pose, edges, depth, etc.). Dynamic updates limited to conditioning_scale changes only; cannot add new ControlNets or change model_id/preprocessor/params without reload.
Show child attributes
Show child attributes
⚠️ NOTE: ControlNet model_ids must be unique. Additionally, they must be compatible with the selected base model.
thibaud/controlnet-sd21-openpose-diffusers, thibaud/controlnet-sd21-hed-diffusers, thibaud/controlnet-sd21-canny-diffusers, thibaud/controlnet-sd21-depth-diffusers, thibaud/controlnet-sd21-color-diffusers, lllyasviel/control_v11f1p_sd15_depth, lllyasviel/control_v11f1e_sd15_tile, lllyasviel/control_v11p_sd15_canny, xinsir/controlnet-depth-sdxl-1.0, xinsir/controlnet-canny-sdxl-1.0, xinsir/controlnet-tile-sdxl-1.0 Strength of the ControlNet's influence on generation. Higher values make the model follow the control signal more strictly. Typical range 0.0-1.0, where 0.0 disables the control and 1.0 applies full control. Default: 1.0
Preprocessor to apply to input frames before feeding to the ControlNet. Common options include 'pose_tensorrt', 'soft_edge', 'canny', 'depth_tensorrt', 'passthrough'. If None, no preprocessing is applied.
⚠️ NOTE: ControlNet preprocessor must be in the available list (AVAILABLE_PREPROCESSORS).
Whether this ControlNet is active. Disabled ControlNets are not loaded. Default: true
Fraction of the denoising process (0.0-1.0) when ControlNet guidance begins. 0.0 means guidance starts from the beginning.
Fraction of the denoising process (0.0-1.0) when ControlNet guidance ends. 1.0 means guidance continues until the end.
IP adapter — Turns on IP-Adapter style conditioning and is fully hot-swappable. Available for SDXL, SDXL-faceid, SD1.5
Show child attributes
Show child attributes
Type of IP adapter. Use 'faceid' for SDXL-faceid models, 'regular' for others
regular, faceid Weight interpolation method for IP adapter style conditioning. Controls how the style influence changes throughout the generation process.
linear, ease in, ease out, ease in-out, reverse in-out, weak input, weak output, weak middle, strong middle, style transfer, composition, strong style transfer, style and composition, style transfer precise, composition precise HTTPS URL of the style image to use. When set, the runtime downloads the image and configures the pipeline; if omitted, a default style image is used. For 'faceid' type, the image must contain a clear face. Available for SDXL, SDXL-faceid, SD1.5
live-video-to-video streamdiffusion, streamdiffusion-sd15, streamdiffusion-sdxl, streamdiffusion-sdxl-faceid