Upload folder using huggingface_hub

.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
+bookimg_16.step_069000.webp filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,37 @@
+# sd 1.5 vae, text trained demo
+
+It has been said that the sd vae is not capable of faithful text rendering,
+at a fundamental level.
+I decided to test that and it turns out to not exactly be true.
+
+This 4channel vae can render a 16pt font with almost perfect fidelity.
+
+This is a TECH DEMO ONLY. I have trained it exclusively on text, so
+normal rendering has drastically suffered as a result. 
+
+# Training details
+This started with the original sd vae.
+I generated an initial dataset of 14pt-only text images, with
+https://github.com/ppbrown/ai-training/blob/main/trainer/vae/gen_glyph_dataset.py
+( around 4000 of them)
+I then trained the vae at LR 1e-5 for 28000 steps, batchsize 1,
+using my standard settings of lpips/vgg weights 0.08, LAP 0.02
+and "rawvgg" enabled, with my train_vae.py in that same repo
+
+I then generated a MIXED size font dataset,ranging across 14,16,18, and 20pt
+total images around 8000
+This time I chose batch size 2, LR 2e-5.
+
+14pt text seems to have a capacity limit for the 4channel vae.
+16pt, however, renders almost indistinguishable from original.
+The specific font used across all images, was
+Libertinus Serif
+
+!(clean 16pt)[bookimg_16.step_069000.webp]
+
+If you want to try it out for yourself, you can use the tools in my repo,
+such as
+
+    trainer/cache-utils/create_imgcache_sdvae.py --vae --previewonly \
+      --model opendiffusionai/sd15vae-texttrained  --data_root someimgdir
+

config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.36.0",
+  "_name_or_path": "sd15_text_14pt-1e-5/step_028000",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7150edb510d8cafaf97e061d01ba1bfda5dbcf2b7a70384a65c27560db9cb235
+size 334643268