You need to agree to share your Hugging Face information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
This is a modified copy of krea/Krea-2-Raw, distributed under the Krea 2 Community License Agreement (LICENSE.pdf in this repository). By agreeing you accept to be bound by its terms and by Krea's Acceptable Use Policy (https://www.krea.ai/krea-2-use-policy).
Log in or Sign Up to review the conditions and access this model content.
Krea 2 Raw FP8 — radiance container
krea/Krea-2-Raw as a single .rad container for the
radiance inference engine (AMD RDNA4, ROCm).
This is not an official Krea product and is not endorsed by Krea.
| File | krea-2-raw-fp8.rad — 16.31 GiB |
| Weights | the text encoder's (Qwen3-VL-4B), the fusion blocks' and the diffusion transformer's linears FP8 E4M3 per 128×128 block (bf16 scales); the q/k norms and the text norm f32 (as released); the small linears, the remaining norms and tables and the VAE bf16 |
| Steps | 28 by default, guidance 4.5 against an empty negative prompt (guidance_scale or true_cfg_scale, and negative_prompt); num_inference_steps sets the count |
| Needs | radiance built from main after 1.8.1 — Krea 2 support is not in 1.8.1 and comes with the next release |
Serve
radiance --model krea-2-raw-fp8.rad --host 0.0.0.0 --port 8000
The server speaks OpenAI's Images API: POST /v1/images/generations (Krea 2 reads only text, so
/v1/images/edits answers 501). Pictures come back as b64_json (png, jpeg or webp). Sizes up to
2048x2048, sides multiples of 16, 1024x1024 by default; seed, n, streaming with partial_images.
RGB only (background: transparent is refused).
38 seconds a 1024x1024 picture at 28 guided steps on two Radeon AI PRO R9700 (gfx1201).
Against diffusers' own bf16 pipeline from the same noise (1024x1024, seed 7), 28 steps at guidance 4.5: PSNR 28.9 dB.
How this file was made
rad-convert krea/Krea-2-Raw --recipe krea-2-fp8.recipe -o krea-2-raw-fp8.rad
krea/Krea-2-Raw is the diffusers download of that repository. The recipe (krea-2-fp8.recipe in this
repository) names what is quantised and cast; everything it does not name is the checkpoint's own dtype
(the release stores some tensors f32, which the casts at the end narrow):
te.blk.*.attn_qkv.weight rtn codes=fp8_e4m3 block=128x128 scale=bf16
te.blk.*.attn_output.weight rtn codes=fp8_e4m3 block=128x128 scale=bf16
te.blk.*.ffn_gate_up.weight rtn codes=fp8_e4m3 block=128x128 scale=bf16
te.blk.*.ffn_down.weight rtn codes=fp8_e4m3 block=128x128 scale=bf16
fuse.*.attn_qkv.weight rtn codes=fp8_e4m3 block=128x128 scale=bf16
fuse.*.attn_gate.weight rtn codes=fp8_e4m3 block=128x128 scale=bf16
fuse.*.attn_output.weight rtn codes=fp8_e4m3 block=128x128 scale=bf16
fuse.*.ffn_gate_up.weight rtn codes=fp8_e4m3 block=128x128 scale=bf16
fuse.*.ffn_down.weight rtn codes=fp8_e4m3 block=128x128 scale=bf16
dit.blk.*.attn_qkv.weight rtn codes=fp8_e4m3 block=128x128 scale=bf16
dit.blk.*.attn_gate.weight rtn codes=fp8_e4m3 block=128x128 scale=bf16
dit.blk.*.attn_output.weight rtn codes=fp8_e4m3 block=128x128 scale=bf16
dit.blk.*.ffn_gate_up.weight rtn codes=fp8_e4m3 block=128x128 scale=bf16
dit.blk.*.ffn_down.weight rtn codes=fp8_e4m3 block=128x128 scale=bf16
fuse.*.norm1.weight cast dtype=f32
fuse.*.norm2.weight cast dtype=f32
fuse.*.q_norm.weight cast dtype=f32
fuse.*.k_norm.weight cast dtype=f32
dit.blk.*.q_norm.weight cast dtype=f32
dit.blk.*.k_norm.weight cast dtype=f32
txt.norm.weight cast dtype=f32
fuse.* cast dtype=bf16
txt.* cast dtype=bf16
dit.* cast dtype=bf16
vae.* cast dtype=bf16
License
Krea 2 is licensed under the Krea 2 Community License Agreement (LICENSE.pdf); NOTICE carries its
attribution notice. Use must also follow Krea's Acceptable Use Policy,
and the license requires deployers to run content filtering. This container is a modified copy: its weights
are re-encoded as described above. The text encoder inside it is Qwen3-VL-4B, under the Apache License 2.0
(LICENSE-Qwen3-VL).
Model tree for StillDeadcode/krea-2-raw-radiance-fp8
Base model
krea/Krea-2-Raw