calcuis/hidream-gguf

---

license: mit language:

• en

base_model:

• HiDream-ai/HiDream-I1-Full

pipeline_tag: text-to-image tags:

• gguf-node

widget:

• text: >-

cute anime girl with massive fluffy fennec ears and a big fluffy tail blonde messy long hair blue eyes wearing a maid outfit with a long black gold leaf pattern dress and a white apron mouth open holding a fancy black forest cake with candles on top in the kitchen of an old dark Victorian mansion lit by candlelight with a bright window to the foggy forest and very expensive stuff everywhere parameters: negative_prompt: >- full (info only, don't copy this) output: url: samples\ComfyUI00004.png

• text: fast (same prompt as full)

output: url: samples\ComfyUI00005.png

• text: dev (same prompt as full)

output: url: samples\ComfyUI00006.png

• text: 1-clip (llama only)

output: url: samples\ComfyUI00001.png

• text: 2-clip (llama + t5xxl)

output: url: samples\ComfyUI00002.png

---

gguf quantized version of HiDream-i1-Full (incl. full + dev + fast + e1 + e1-1)

• full set gguf works right away (all gguf: model + encoder + vae)
• upgrade your node(pypi|repo|pack) for model support

!screenshot

setup

• drag hidream to > ./ComfyUI/models/diffusionmodels
• drag encoder: g, l, t5xxl and llama to > ./ComfyUI/models/textencoders
• drag pig to > ./ComfyUI/models/vae

workflow

• drag the json file or demo picture below for example workflow

reference

• base model from hidream-ai
• get safetensors from comfy-org
• get more t5xxl-encoder gguf here
• get more lama3.1-8b-encoder gguf here