zeromodels
/

stable-diffusion-3.5-large

@@ -26,7 +26,7 @@ tags:
 # Run Stable Diffusion 3.5 with Keras 3: JAX, PyTorch, or TensorFlow
-[![GitHub](https://img.shields.io/badge/GitHub-ZeroModels-181717?logo=github)](https://github.com/IMvision12/ZeroModels) [![Docs](https://img.shields.io/badge/Docs-Stable_Diffusion_3.5-1f6feb)](https://imvision12.github.io/ZeroModels/stable_diffusion_3_5/) [![HuggingFace](https://img.shields.io/badge/HuggingFace-Stable_Diffusion_3.5-ffd21e?logo=huggingface&logoColor=black)](https://huggingface.co/collections/zeromodels/stable-diffusion-v35-6aa7963880e76656e5646ffc)
 **Powered by Stability AI**
@@ -73,13 +73,13 @@ import os
 os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
 from PIL import Image
-from zeromodels.models.stable_diffusion_3_5 import StableDiffusion3_5TextToImage, StableDiffusion3_5Tokenizer
-model = StableDiffusion3_5TextToImage.from_weights(
     "zeromodels/stable-diffusion-3.5-large",
     text_encoder_3="zeromodels/t5-v1_1-xxl-encoder",  # optional: omit to zero the T5 features
 )
-tokenizer = StableDiffusion3_5Tokenizer.from_weights("zeromodels/stable-diffusion-3.5-large")
 inputs = tokenizer("a photograph of an astronaut riding a horse")
 images = model.generate(**inputs, num_inference_steps=28, guidance_scale=3.5, seed=0)
@@ -103,18 +103,20 @@ Load any Stable Diffusion 3.5 checkpoint the same way with `from_weights("zeromo
 ## Tips
 - Set `KERAS_BACKEND` **before** importing Keras / zeromodels.
 - The graphs are built for 1024px. Pass `transformer_sample_size=<px / 8>, vae_sample_size=<px>` to
   `from_weights` to build for another multiple of 16px (the weights are resolution-independent
   up to the 3072px position grid).
-- `StableDiffusion3_5Model.from_weights(...)` loads the same repo as the bare container
-  (`.transformer` / `.vae` / `.text_encoder` / `.text_encoder_2`) without the generation loop.
 - `model.text_encoder_3` can be any `SD3T5EncoderModel` (for example one loaded with
-  `quantization="int8"`); it is not part of the container's weights.
 - Both `channels_last` and `channels_first` are supported (`keras.config.set_image_data_format`
   before loading); `generate` always returns `(batch, H, W, 3)` uint8.
 - On-the-fly `hf:` conversion is not supported for diffusion models; the checkpoints are
   hosted here, converted once.
-- See the [Stable Diffusion 3.5 docs](https://imvision12.github.io/ZeroModels/stable_diffusion_3_5/).
 ## License

 # Run Stable Diffusion 3.5 with Keras 3: JAX, PyTorch, or TensorFlow
+[![GitHub](https://img.shields.io/badge/GitHub-ZeroModels-181717?logo=github)](https://github.com/IMvision12/ZeroModels) [![Docs](https://img.shields.io/badge/Docs-Stable_Diffusion_3.5-1f6feb)](https://imvision12.github.io/ZeroModels/diffusers/#stable-diffusion-3-5) [![HuggingFace](https://img.shields.io/badge/HuggingFace-Stable_Diffusion_3.5-ffd21e?logo=huggingface&logoColor=black)](https://huggingface.co/collections/zeromodels/stable-diffusion-v35-6aa7963880e76656e5646ffc)
 **Powered by Stability AI**
 os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
 from PIL import Image
+from zeromodels.diffusers import ZMDiffusion, ZMDiffusionTokenizer
+model = ZMDiffusion.from_weights(
     "zeromodels/stable-diffusion-3.5-large",
     text_encoder_3="zeromodels/t5-v1_1-xxl-encoder",  # optional: omit to zero the T5 features
 )
+tokenizer = ZMDiffusionTokenizer.from_weights("zeromodels/stable-diffusion-3.5-large")
 inputs = tokenizer("a photograph of an astronaut riding a horse")
 images = model.generate(**inputs, num_inference_steps=28, guidance_scale=3.5, seed=0)
 ## Tips
 - Set `KERAS_BACKEND` **before** importing Keras / zeromodels.
+- `AutoZModel` / `AutoZMTokenizer` (`from zeromodels import ...`) load this repo too;
+  they resolve to `ZMDiffusion` / `ZMDiffusionTokenizer` from its `model_type`.
 - The graphs are built for 1024px. Pass `transformer_sample_size=<px / 8>, vae_sample_size=<px>` to
   `from_weights` to build for another multiple of 16px (the weights are resolution-independent
   up to the 3072px position grid).
+- The trained components are attributes of the loaded `ZMDiffusion`
+  (`.transformer` / `.vae` / `.text_encoder` / `.text_encoder_2`), each callable on its own.
 - `model.text_encoder_3` can be any `SD3T5EncoderModel` (for example one loaded with
+  `quantization="int8"`); it is not part of this checkpoint's weights.
 - Both `channels_last` and `channels_first` are supported (`keras.config.set_image_data_format`
   before loading); `generate` always returns `(batch, H, W, 3)` uint8.
 - On-the-fly `hf:` conversion is not supported for diffusion models; the checkpoints are
   hosted here, converted once.
+- See the [Stable Diffusion 3.5 docs](https://imvision12.github.io/ZeroModels/diffusers/#stable-diffusion-3-5).
 ## License

zm_config.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
   "library_name": "zeromodels",
   "zeromodels_version": "1.3.3",
-  "model_module": "zeromodels.models.stable_diffusion_3_5",
-  "model_class": "StableDiffusion3_5Model",
   "variant": "stable-diffusion-3.5-large",
   "weights": "model.weights.json",
   "schema_version": 2,
@@ -85,4 +85,4 @@
     "num_inference_steps": 28,
     "guidance_scale": 3.5
   }
-}

 {
   "library_name": "zeromodels",
   "zeromodels_version": "1.3.3",
+  "model_module": "zeromodels.diffusers",
+  "model_class": "ZMDiffusion",
   "variant": "stable-diffusion-3.5-large",
   "weights": "model.weights.json",
   "schema_version": 2,
     "num_inference_steps": 28,
     "guidance_scale": 3.5
   }
+}

zm_preprocessor.json ADDED Viewed

	@@ -0,0 +1,11 @@

+{
+  "library_name": "zeromodels",
+  "zeromodels_version": "1.3.3",
+  "preprocessor_module": "zeromodels.diffusers",
+  "preprocessor_class": "ZMDiffusionTokenizer",
+  "variant": "stable-diffusion-3.5-large",
+  "model_type": "stable_diffusion_3_5",
+  "max_seq_len": 77,
+  "pad_token": "<|endoftext|>",
+  "max_sequence_length": 256
+}