Corwin Black

Mescalamba

AI & ML interests

image denoising

Recent Activity

new activity about 2 months ago

calcuis/lumina-gguf:Gemma 2 2b quantized doesn't work

new activity about 2 months ago

Alpha-VLLM/Lumina-Image-2.0:When I run in comfyui

new activity 2 months ago

Comfy-Org/Lumina_Image_2.0_Repackaged:Prompt ComfyUI image VS Offical demo

View all activity

Organizations

None yet

Mescalamba's activity

New activity in calcuis/lumina-gguf about 2 months ago

Gemma 2 2b quantized doesn't work

#1 opened 2 months ago by

eeditor1055

New activity in Alpha-VLLM/Lumina-Image-2.0 about 2 months ago

When I run in comfyui

#10 opened 2 months ago by

layde

New activity in Comfy-Org/Lumina_Image_2.0_Repackaged 2 months ago

Prompt ComfyUI image VS Offical demo

#2 opened 2 months ago by

Dakerqi

replied to m-ric's post 4 months ago

Pretty cool. Could use something like that, just bit bigger, to replace T5-XL and T5-XXL.

replied to mlabonne's post 4 months ago

Any LLM?

Im not sure its possible for thing like T5 XXL, which is kinda unfortunate cause that stupid thing is used for quite a few image diffusion models as input and its censored pretty heavily even as encoder only part.

New activity in kxdw2580/Qwen2.5-3B-Instruct-Uncensored-Test 4 months ago

Very good!

#1 opened 4 months ago by

Mescalamba

New activity in Djrango/Qwen2vl-Flux 4 months ago

It does seem really cool but..

#9 opened 4 months ago by

Mescalamba

New activity in migtissera/Llama-3-8B-Synthia-v3.5 5 months ago

Its really good but..

#3 opened 5 months ago by

Mescalamba

New activity in nyanko7/flux-dev-de-distill 6 months ago

It's a great experimental project! how can I run the model on ComfyUI and get the best result?

#1 opened 7 months ago by

wikeeyang

New activity in Freepik/flux.1-lite-8B-alpha 6 months ago

Possible to work with 8GB VRAM and 16GB RAM?

#7 opened 6 months ago by

krigeta

New activity in city96/flux.1-lite-8B-alpha-gguf 6 months ago

need fp8 for speed

#1 opened 6 months ago by

Ai11Ali