Text-to-Image
Diffusers
Safetensors
English
Flux2KleinPipeline
flux2_klein
image-editing
diffusion
quantized
quantfunc
flux
Instructions to use QuantFunc/Klein-9B-Series with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use QuantFunc/Klein-9B-Series with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("QuantFunc/Klein-9B-Series", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
sync precision-config/40x-int4-f8-sample.json from ModelScope
Browse files
precision-config/40x-int4-f8-sample.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_comment": "FLUX.2-klein 40x \u2014 RTX 40 / Ada (SM89, FP8-capable but no FP4). Attention + FFN INT4; modulation + embedders + head FP8.",
|
| 3 |
+
"transformer_blocks.attn": "i4",
|
| 4 |
+
"transformer_blocks.ff": "i4",
|
| 5 |
+
"transformer_blocks.ff_context": "i4",
|
| 6 |
+
"single_transformer_blocks.attn": "i4",
|
| 7 |
+
"double_stream_modulation_img": "f8",
|
| 8 |
+
"double_stream_modulation_txt": "f8",
|
| 9 |
+
"single_stream_modulation": "f8",
|
| 10 |
+
"x_embedder": "f8",
|
| 11 |
+
"context_embedder": "f8",
|
| 12 |
+
"norm_out": "f8",
|
| 13 |
+
"proj_out": "f8",
|
| 14 |
+
"time_guidance_embed": "f8"
|
| 15 |
+
}
|