Resources you need:
📂Files :
24 gb Vram : base
16 gb Vram: Q8_0
12 gb Vram: Q5_K_S
<12 gb Vram: Q4_K_S
For base version
Model : hidream_i1_dev_fp8.safetensors
in ComfyUI\models\diffusion_models
For GGUF version
GGUF_Model : hidream-i1-dev-QX_K_S.gguf
in ComfyUI\models\unet
VAE : ae.safetensors
in ComfyUI\models\vae
CLIP : clip_l_hidream.safetensors, clip_g_hidream.safetensors, t5xxl_fp8_e4m3fn_scaled.safetensors and llama_3.1_8b_instruct_fp8_scaled.safetensors
in ComfyUI\models\clip
📦Custom Nodes :
Description
Base version
FAQ
Comments (3)
Will this work on full size images? I I have some upscaled images that are 4000x6000 but obviously that would be very difficult to process on my 8gb/vram machine.
If you have just a subsection you want to inpaint, use something like gimp to cut out a manageable section. Then inpaint just that section. Afterwards, copy it as a layer and carefully position it back into your image.
What LoRA's are used for this HiDream model??