VERIGEN commited on
Commit
5eb82a5
·
1 Parent(s): 60219f9

Model card, manifest, buffalo_l detection and recognition models

Browse files
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - krea2
5
+ - lora-training
6
+ private: true
7
+ ---
8
+
9
+ # VForge-Krea2
10
+
11
+ Model files for [vforge](https://github.com/verigen/vforge) (`k2t` trains Krea 2 LoRAs, `k2c` compares them by face
12
+ likeness). Private: the files carry upstream licences that apply to every use.
13
+
14
+ `k2t model fetch VERIGEN/VForge-Krea2[:ALIAS]` downloads the files listed in `manifest.json`, checks their sha256
15
+ and registers the aliases in `~/.config/k2t/config.toml`. The aliases match the defaults `k2t project init` writes,
16
+ so a fetched set works with a new project as is.
17
+
18
+ ## Layout
19
+
20
+ | Path | Alias | Content |
21
+ |---|---|---|
22
+ | `dit/krea2-raw.int8.k2q.safetensors` | `krea2-int8` | Krea 2 Raw DiT, block Linears pre-quantised to INT8 |
23
+ | `dit/krea2-raw.nf4.k2q.safetensors` | `krea2-nf4` | Krea 2 Raw DiT, block Linears pre-quantised to NF4 |
24
+ | `vae/qwen-image-vae.safetensors` | `qwen-image-vae` | Qwen-Image VAE |
25
+ | `text_encoder/qwen3vl-4b.fp8_scaled.safetensors` | `qwen3vl-4b-fp8` | Qwen3-VL-4B text encoder, fp8_scaled |
26
+ | `lora/krea2-turbo-r64.safetensors` | `krea2-turbo-r64` | Krea 2 turbo LoRA, rank 64 (previews and k2c renders) |
27
+ | `face/buffalo_l/` | `buffalo_l` | InsightFace detection (`det_10g.onnx`) and recognition (`w600k_r50.onnx`) |
28
+ | `compile/<env key>/k2t-cc.zip` | | `k2t compile-cache export` bundle for one GPU model and torch build |
29
+
30
+ `.k2q` files load as-is: `k2t model verify FILE` checks the header, layout and checksum. The source sha256, the
31
+ quantisation and the format version are in the safetensors header.
32
+
33
+ A compile bundle only helps on the exact GPU model and torch / Triton / CUDA build in its env key (`k2t env` prints
34
+ the local one). `k2t compile-cache import` refuses a bundle made for another key.
35
+
36
+ Versions are this repository's revisions. A changed file replaces the old one in place, and `k2t model fetch
37
+ --revision` pins an earlier revision.
38
+
39
+ ## Licences
40
+
41
+ | Files | Source | Licence |
42
+ |---|---|---|
43
+ | `face/buffalo_l/` | [InsightFace](https://github.com/deepinsight/insightface) `buffalo_l` | the code is MIT; the pretrained models are for non-commercial research use only |
44
+
45
+ The `.k2q` files are converted by vforge from the upstream weights. Each file's row in this table is added together
46
+ with the file, and the upstream licence texts go into `LICENSES/`.
face/buffalo_l/det_10g.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5838f7fe053675b1c7a08b633df49e7af5495cee0493c7dcf6697200b85b5b91
3
+ size 16923827
face/buffalo_l/w600k_r50.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c06341c33c2ca1f86781dab0e829f88ad5b64be9fba56e56bc9ebdefc619e43
3
+ size 174383860
manifest.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "format": 1,
3
+ "models": {
4
+ "buffalo_l": {
5
+ "kind": "face",
6
+ "dir": "face/buffalo_l",
7
+ "files": {
8
+ "det_10g.onnx": "5838f7fe053675b1c7a08b633df49e7af5495cee0493c7dcf6697200b85b5b91",
9
+ "w600k_r50.onnx": "4c06341c33c2ca1f86781dab0e829f88ad5b64be9fba56e56bc9ebdefc619e43"
10
+ }
11
+ }
12
+ },
13
+ "compile": {}
14
+ }