Generate an image or batch of images from a text description using the fixed HiDream I1 Fast FP8 model. No uploaded media is required.
Workflow details
Laufzeitprofil
Quellen
1 QuelleHover nodes for Pipe controls
Core
Primary Pipe surface
Prompt
CLIPTextEncode
Output size
EmptySD3LatentImage
Extended
Additional surfaced controls
Sampling
KSampler
Negative prompt
CLIPTextEncode
Sampling schedule shift
ModelSamplingSD3
Hardware and download-size estimates are not available yet.
Anforderungen
VAE · Hugging Face · Comfy-Org/HiDream-I1_ComfyUI
Text encoder · Hugging Face · Comfy-Org/HiDream-I1_ComfyUI
Text encoder · Hugging Face · Comfy-Org/HiDream-I1_ComfyUI
hidream_i1_fast_fp8.safetensors
Datei ungeprüftCheckpoint · Hugging Face · Comfy-Org/HiDream-I1_ComfyUI
llama_3.1_8b_instruct_fp8_scaled.safetensors
Datei ungeprüftText encoder · Hugging Face · Comfy-Org/HiDream-I1_ComfyUI
t5xxl_fp8_e4m3fn_scaled.safetensors
Datei ungeprüftText encoder · Hugging Face · Comfy-Org/HiDream-I1_ComfyUI
Knotenpaket · GitHub · tea-time-labs/sweet-tea-nodes