ComfyUI Node: Emu 3.5 X2I (Image Edit)
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
Emu3.5
Inputs
model EMU_MODEL
tokenizer EMU_TOKENIZER
vq_model EMU_VQ
prompt STRING
reference_image_1 IMAGE
image_area
- 256x256 (65536) - Fastest
- 384x384 (147456)
- 512x512 (262144) - Recommended
- 640x640 (409600)
- 768x768 (589824)
- 1024x1024 (1048576) - High VRAM
cfg_scale FLOAT
seed INT
reference_image_2 IMAGE
reference_image_3 IMAGE
image_top_k INT
image_temperature FLOAT
tiled_decode BOOLEAN
tile_size INT
Outputs
IMAGE
STRING
STRING
Extension: Emu35-Comfyui-Nodes
ComfyUI integration for BAAI's Emu3.5 multimodal models for text-to-image generation and multimodal understanding. (Description by CC)
Authored by EricRollei
Looking for a different node?
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.