Alvaro Somoza

OzzyGT's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in OzzyGT/4xRemacri about 7 hours ago

Format

3

#1 opened 4 days ago by

TheMolan

New activity in OzzyGT/MiniMax_H3_sdnq_8bit_pruned about 1 month ago

Can you make a HQ quant for SDNQ?

👍 1

2

#1 opened about 1 month ago by

wtrida19933

Isn't it better to enable use_quantized_matmul?

1

#2 opened about 1 month ago by

wtrida19933

New activity in OzzyGT/MiniMax_H3_sdnq_dynamic_8bit about 1 month ago

vae: mixed fp16 decoder + fp32 encoder/scales, single shard

#1 opened about 1 month ago by

OzzyGT

New activity in OzzyGT/MiniMax_H3_sdnq_dynamic_4bit about 1 month ago

vae: mixed fp16 decoder + fp32 encoder/scales, single shard

#2 opened about 1 month ago by

OzzyGT

Could You tell me how to use this model?

1

#1 opened about 1 month ago by

makao008

New activity in OzzyGT/diffusers-fast-inpaint 3 months ago

What happened? It doesnot work for half year?

6

#19 opened 7 months ago by

BondGoga

New activity in OzzyGT/ERNIE_Image_Turbo_sdnq_dynamic_int4 5 months ago

Unrecognized keys and unexpected types

2

#1 opened 5 months ago by

SamuelTallet

New activity in diffusers/FLUX.2-dev-bnb-4bit 5 months ago

2 gpu

9

#3 opened 5 months ago by

goodasdgood

New activity in stable-diffusion-v1-5/stable-diffusion-v1-5 7 months ago

Dependencies version for stabble difussion v1.5

1

#39 opened 7 months ago by

lightshadown

New activity in diffusers/FLUX.2-dev-bnb-4bit 7 months ago

ValueError: state dict does not contain bitsandbytes__* / quantized_stats when loading sharded bnb-4bit FLUX.2 pipeline via DiffusionPipeline.from_pretrained

6

#2 opened 7 months ago by

pmlakner

New activity in OzzyGT/Qwen-Image-2512-bnb-4bit-transformer 8 months ago

can you please provide an example?

👍 1

8

#1 opened 8 months ago by

gabbo1995

New activity in diffusers/stable-diffusion-xl-inpainting 8 months ago

changes for ZeroGPU

#44 opened 8 months ago by

linoyts

New activity in diffusers/FLUX.2-dev-bnb-4bit 10 months ago

Does this work in Comfyui?

👍 1

3

#1 opened 10 months ago by

Winnougan

New activity in OzzyGT/diffusers-fast-inpaint 12 months ago

Zero GPU worker Error

1

#18 opened 12 months ago by

7uj8ui

New activity in discord-community/README 12 months ago

How to solve device mismatch issue when using offloading with QwenImageEditPlus pipeline and GGUF weights

3

#10 opened 12 months ago by

sadimanna

New activity in OzzyGT/qwen-image-lighting-gguf about 1 year ago

Architecture tag isn't compatible with ComfyUI-GGUF

👍 2

1

#1 opened about 1 year ago by

CognitiveSourceress

New activity in OzzyGT/diffusers-image-fill about 1 year ago

huggingface upgrade their ModelMixin._load_pretrained_model() lead this space unusable

2

#9 opened about 1 year ago by

BeBubble

New activity in Qwen/Qwen-Image-Edit about 1 year ago

HW requirements

➕ 25

30

#6 opened about 1 year ago by

vladciocan88

New activity in Qwen/Qwen-Image about 1 year ago

Update README.md to include quantization code snippets for 24GB and 16GB GPUs

🚀🔥 7

6

#27 opened about 1 year ago by

OzzyGT