calcuis/omnigen2-gguf

gguf quantized version of omnigen2

• drag omnigen2 to > ./ComfyUI/models/diffusion_models
• drag qwen2.5 to > ./ComfyUI/models/text_encoders
• drag pig to > ./ComfyUI/models/vae

Prompt

the anime girl with massive fennec ears is wearing cargo pants while sitting on a log in the woods biting into a sandwitch beside a beautiful alpine lake

Prompt

the anime girl with massive fennec ears is wearing cargo pants while sitting on a log in the woods biting into a sandwitch beside a beautiful alpine lake

Prompt

the anime girl with massive fennec ears is wearing cargo pants while sitting on a log in the woods biting into a sandwitch beside a beautiful alpine lake

• don't need safetensors anymore; all gguf (model + encoder + vae)
• full set gguf works on gguf-node (see the last item from reference below)

• t2i is roughly 3x to 5x faster than i2i or image editing
• get more qwen2.5 gguf encoder here (for this encoder, to ensure the embedded visual/vision part of tensors working properly, especially if you need image input, it's recommended to take q4 or above)
• alternatively, you could get fp8-e4m3fn safetensors encoder here, or make it with TENSOR Cutter (Beta); works pretty good as well; and don't even need to switch loader (gguf clip loader supports scaled fp8 safetensors)

reference

• base model from omnigen2
• comfyui from comfyanonymous
• gguf-node (pypi|repo|pack)