made some changes to the nodes. do a git pull and re-run requirements.
MUST USE NEW TEST WORKFLOW!!!! there are new nodes to unload weight of first model.
if it runs for you, please post your generations in the discussions!!!!! i cant run it, its too big at 30gb of total size with everything.
model details below with node link.
V
EXPERIMENTAL! do not expect it to work until i change the model card giving confirmation that it does work. im constantly updating the nodes to get it to run! keep git pulling. just merged the files to match another contributors workflow. this will lessen the requirements for lower vram users. its still a 16gb fp8 model and the SR model to upscale it heavy as well. working on offloading implementation without sage or triton. it will be in the workflow once i test it. i will update the repo with a SEPERATE offloading workflow check back soon.
THIS MODEL WILL NOT RUN WITHOUT MY CUSTOM NODE SET. ITS CURATED FOR THIS MODEL SPECIFICALLY!
t5gemma text encoder gguf goes in "gguf" folder NOT text encoder folder
requires these custom nodes (i forked the node set to include fp8 models): https://github.com/RealRebelAI/ComfyUI_MagiHuman_fp8_ditFIX_nodes
files are in the repo
fp8 model - Diffusion models folder
text encoder gguf - gguf folder, NOT text encoder folder
wan vae - vae folder
sd audio vae - vae folder
turbo vae - vae folder
sr fp8 model - diffusion models folder