Dupe-R-IMG: merge DiT + T5 encoder + VAE (297.5M)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+supra2img.himg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,99 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-to-image
+tags:
+- image
+- text-to-image
+- duper
+- dit
+- rectified-flow
+---
+
+# Dupe-R-IMG
+
+The **Supra2-IMG** denoiser, the **flan-t5-base** encoder and the **sd-vae-ft-mse** VAE
+packed into one `model.safetensors`
+
+| section | params | source | license |
+|---|---|---|---|
+| `dit.*` | 104,193,168 | [SupraLabs/Supra2-IMG](https://huggingface.co/SupraLabs/Supra2-IMG) | apache-2.0 |
+| `text_encoder.*` | 109,628,544 | [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) | apache-2.0 |
+| `vae.*` | 83,653,863 | [stabilityai/sd-vae-ft-mse](https://huggingface.co/stabilityai/sd-vae-ft-mse) | mit |
+| **total** | **297,475,575** | | |
+
+## What this is
+
+A **repackaging, not a weight blend**. The DiT was trained against exactly these two
+encoders, so averaging anything would break it. Every tensor is copied unmodified and
+re-namespaced:
+
+- `dit.*` — SupraDiT denoiser, 14 blocks, d_model 576, patch 2
+- `text_encoder.*` — T5 encoder stack, `shared.weight` token embedding included
+- `vae.*` — full AutoencoderKL
+
+Not bundled: the T5 `decoder.*` stack (113M) and `lm_head.weight` (24.7M). Text-to-image
+never runs the seq2seq half.
+
+## Files
+
+| file | size | what |
+|---|---|---|
+| `model.safetensors` | ~567 MB | all 297,475,575 params, prefixed `dit.` / `text_encoder.` / `vae.` |
+| `supra2img.himg` | supra2img converted to .himg ~417 MB |  `mmap` `PROT_READ`, zero-copy load |
+| `model_final_ema.pt` | ~416 MB | untouched upstream checkpoint (bf16) |
+| `config.json` | | geometry, per-section param counts, component provenance |
+| `vae_config.json` | | native `AutoencoderKL` config (separate name on purpose) |
+| `tokenizer.json`, `spiece.model`, … | | flan-t5 tokenizer |
+
+Prefer `.himg` when memory is tight: so a 417 MB model
+costs no resident RAM. `model.safetensors` is the portable single-file form.
+
+## Precision
+
+Stored `float16`, **compute `float32`** (upcast on load). Storage-only: a build comparing
+the C core against a PyTorch reference from this same file still agrees at 1e-6, since
+both read identical bytes. Only parity against the original upstream checkpoint moves
+(~1e-3), which is not visible in a pixel. The `.himg` is exact float32 if you need bit
+parity.
+
+## Specs
+
+| | |
+|---|---|
+| resolution | 256x256 |
+| latent | 4 x 32 x 32 |
+| context | 128 tokens (flan-t5-base) |
+| sampler | rectified flow, Euler (Heun supported) |
+| default steps / cfg | 50 / 3.0 |
+| latent scale | 0.18215 |
+
+## Usage
+
+```python
+import json
+from huggingface_hub import hf_hub_download
+from safetensors import safe_open
+from diffusers import AutoencoderKL
+
+repo = "ShimbaLLM/Dupe-R-IMG"
+dit_sd, te_sd, vae_sd = {}, {}, {}
+with safe_open(hf_hub_download(repo, "model.safetensors"), framework="pt") as f:
+    for k in f.keys():
+        (dit_sd if k.startswith("dit.") else
+         te_sd if k.startswith("text_encoder.") else
+         vae_sd)[k.split('.', 1)[1]] = f.get_tensor(k).float()
+
+vae = AutoencoderKL.from_config(
+    json.load(open(hf_hub_download(repo, "vae_config.json"))))
+vae.load_state_dict(vae_sd)
+```
+
+The T5 encoder stack and the SupraDiT module definitions are in `config.json` under
+`components`, and in the notebook that produced this release.
+
+## Licenses
+
+Bundled components keep their own licenses and carry independent provenance in
+`config.json`: DiT apache-2.0 (SupraLabs), T5 encoder apache-2.0 (Google), VAE mit
+(Stability AI). All three permit redistribution, individually and combined.

config.json

@@ -0,0 +1,87 @@
+{
+  "model_type": "duper_img",
+  "repo_id": "ShimbaLLM/Dupe-R-IMG",
+  "total_params": 297377143,
+  "n_tensors": 596,
+  "storage_dtype": "float16",
+  "compute_dtype": "float32",
+  "tensor_sections": [
+    "dit",
+    "text_encoder",
+    "vae"
+  ],
+  "section_params": {
+    "dit": 104094736,
+    "text_encoder": 109628544,
+    "vae": 83653863
+  },
+  "image_size": 256,
+  "latent_size": 32,
+  "context_length": 128,
+  "latent_scaling_factor": 0.18215,
+  "components": {
+    "dit": {
+      "_class_name": "SupraDiT",
+      "source": "SupraLabs/Supra2-IMG",
+      "license": "apache-2.0",
+      "params": 104094736,
+      "latent_ch": 4,
+      "latent_size": 32,
+      "patch": 2,
+      "d_model": 576,
+      "depth": 14,
+      "n_heads": 9,
+      "mlp_ratio": 4.0,
+      "ctx_dim": 768,
+      "max_ctx": 128,
+      "img_size": 256
+    },
+    "text_encoder": {
+      "_class_name": "T5EncoderModel",
+      "source": "google/flan-t5-base",
+      "license": "apache-2.0",
+      "params": 109628544,
+      "note": "encoder stack only; decoder not bundled",
+      "d_model": 768,
+      "num_layers": 12,
+      "num_heads": 12,
+      "d_ff": 2048,
+      "d_kv": 64,
+      "feed_forward_proj": "gated-gelu",
+      "vocab_size": 32128,
+      "n_positions": 512
+    },
+    "vae": {
+      "_class_name": "AutoencoderKL",
+      "source": "stabilityai/sd-vae-ft-mse",
+      "license": "mit",
+      "params": 83653863,
+      "in_channels": 3,
+      "out_channels": 3,
+      "latent_channels": 4,
+      "block_out_channels": [
+        128,
+        256,
+        512,
+        512
+      ],
+      "layers_per_block": 2,
+      "norm_num_groups": 32,
+      "act_fn": "silu",
+      "scaling_factor": 0.18215,
+      "sample_size": 256
+    },
+    "sampler": {
+      "type": "rectified_flow",
+      "time_range": [
+        0.0,
+        1.0
+      ],
+      "default_steps": 50,
+      "default_cfg_scale": 3.0,
+      "default_sampler": "euler",
+      "supports_heun": true
+    }
+  },
+  "notes": "Repackaging of Supra2-IMG + flan-t5-base (encoder) + sd-vae-ft-mse. Tensors copied unmodified under dit./text_encoder./vae. prefixes; upcast to float32 at load. Not a weight blend."
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1eb3c6f441a6300590ff5eb79c9f00171c66dc43659e019221e35b8bb6e637e
+size 594821830

model_final_ema.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e96aa0537e0fd120af82b3a606dd50c90ae079ac7aa97b38a8da4882daeeee48
+size 416651529

special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

supra2img.himg

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96063c5be9980786da79dc5b041aa279fa56a325e92f386e4a9cf91c51fc87a5
+size 416673792

tokenizer_config.json

@@ -0,0 +1,113 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "name_or_path": "google/t5-v1_1-base",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-base/snapshots/650d7745bf1e502d6949b22cc19155cd656d3d4e/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

vae_config.json

@@ -0,0 +1,29 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.4.2",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 256,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}