gguf quantized and fp8 scaled versions of illustrious (test pack)

Prompt

masterpiece, best quality, vibrant, very aesthetic, high contrast, semrealistic, highly detailed, absurdres, masterful composition, cinematic lighting, score_9, score_8_up, score_7_up, score_6_up, score_5_up, rating_questionable, source_anime, 1girl, portrait, multicolored hair, fringe, bare shoulders, upper body, cosmic

Negative Prompt

femboy, low quality, 2koma, 4koma, bad anatomy, jpeg artifacts, signature, watermark, lowres, bad hands

Prompt

drag it to browser <metadata> same descriptor to the 1st one with gguf q4_0

Prompt

drag it to browser <metadata> same descriptor to the 1st one with gguf q4_0

Prompt

drag it to browser <metadata> same descriptor to the 1st one with gguf q4_0 (new v90 model)

Prompt

drag it to browser <metadata> same descriptor to the 1st one with gguf q4_0 (new v90 model)

Prompt

drag it to browser <metadata> same descriptor to the 1st one with gguf q5_0 (new v90 model)

setup (in general)

• drag gguf file(s) to diffusion_models folder (./ComfyUI/models/diffusion_models)
• drag clip or encoder(s), i.e., illustrious_g_clip and illustrious_l_clip, to text_encoders folder (./ComfyUI/models/text_encoders)
• drag vae decoder(s), i.e., vae, to illustrious_vae folder (./ComfyUI/models/vae)

run it straight (no installation needed way)

• get the comfy pack with the new gguf-node (pack)
• run the .bat file in the main directory

workflow

• drag any workflow json file to the activated browser; or
• drag any generated output file (i.e., picture, video, etc.; which contains the workflow metadata) to the activated browser

review

• use tag/word(s) as input for more accurate results for those legacy models; not very convenient (compare to the recent models) at the very beginning
• credits should be given to those contributors from civitai platform
• fast-illustrious gguf was quantized from fp8 scaled safetensors while illustrious gguf was quantized from the original bf16 (this is just an attempt to test: is it true? the trimmed model with 50% tensors lesser really load faster? please test it yourself; btw, some models might have their unique structure/feature affecting the loader performance, never one size fits all)
• fp8 scaled file works fine in this model; including vae and clips
• good to run on old machines, i.e., 9xx series or before (legacy mode [--disable-cuda-malloc --lowvram] supported); compatible with the new gguf-node
• disclaimer: some models (original files) are provided by someone else and we might not easily spot out the creator/contributor(s) behind, unless it was specified in the source; rather let it blank instead of anonymous/unnamed/unknown; if it is your work, do let us know; we will address it back properly and probably; thanks for everything

reference

• wai creator
• comfyui comfyanonymous
• gguf-node (pypi|repo|pack)