Instructions to use ayjays132/Phillnet-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ayjays132/Phillnet-2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ayjays132/Phillnet-2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ayjays132/Phillnet-2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ayjays132/Phillnet-2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ayjays132/Phillnet-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ayjays132/Phillnet-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ayjays132/Phillnet-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ayjays132/Phillnet-2

SGLang

How to use ayjays132/Phillnet-2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ayjays132/Phillnet-2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ayjays132/Phillnet-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ayjays132/Phillnet-2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ayjays132/Phillnet-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ayjays132/Phillnet-2 with Docker Model Runner:
```
docker model run hf.co/ayjays132/Phillnet-2
```

Phillnet-2 / ImageGen /README.md

ayjays132

Upload 470 files

ad2ce18 verified 1 day ago

preview code

raw

history blame contribute delete

3.77 kB

ImageGen

HF-compatible package for the trained local text-to-image adapter.

Files

adapter_model.pt: trained adapter weights. This file is preserved and is not regenerated by setup scripts.
config.json: adapter and image-generator architecture.
training_config.json: training provenance and trainable tensor list.
model_index.json: Hugging Face/Diffusers-style entry metadata.
pipeline.py: ImageGenPipeline.from_pretrained(...) and generation wrapper.
quality_adapter.pt: sidecar latent quality adapter trained without replacing the base adapter checkpoint.
visual_contract_adapter.pt: sidecar Visual Contract Adapter for prompt/layout control. It is initialized as a safe no-op until VCA-specific training.
model/: adapter, Qwen-aligned text refiner, LoRA helpers, and latent diffusion scheduler.
tokenizer/: local tokenizer used for prompt tokenization.
models/Phillnet-2-SDXL-UNet-VAE/: packaged local UNet, VAE, and scheduler config for the diffusion route.
models/Phillnet-2-SDXL-TextEncoders/: packaged SDXL Turbo tokenizers/text encoders used for prompt-faithful diffusion conditioning.

Load

from ImageGen import ImageGenPipeline

pipe = ImageGenPipeline.from_pretrained("ImageGen", device="cpu")
out = pipe("a geometric neon logo", height=128, width=128, num_inference_steps=1)
image = out.images[0]

For coherent Qwen conditioning, pass the already-loaded local Qwen/GptOss text model:

pipe = ImageGenPipeline.from_pretrained("ImageGen", text_model=qwen_model, tokenizer=qwen_tokenizer, device="cuda")

By default the pipeline uses the trained text-prior route with the non-destructive quality adapter enabled:

out = pipe("studio photo of a glass sculpture", height=128, width=128)

Use quality_strength=0.0 to recover the unmodified base adapter behavior. The generation_strategy="diffusion" uses the packaged SDXL Turbo text encoders plus the local UNet/VAE route. Use it for prompt-faithful public examples:

out = pipe(
    "wireless headphones product photo on a clean desk, soft studio light",
    height=128,
    width=128,
    num_inference_steps=1,
    generation_strategy="diffusion",
)

The Visual Contract Adapter is exposed separately:

out = pipe(
    'woman in a blue jacket holding a yellow umbrella, poster text says "RAIN DAY"',
    height=128,
    width=128,
    contract_strength=1.0,
)

The VCA checkpoint is saved outside adapter_model.pt, starts as a zero-output residual, and uses existing Qwen/text conditioning tokens plus optional contract_maps tensors. This keeps the base weights reversible and lets future training target prompt obedience, layout, edit masks, and exact-text constraints.

PhillMagine320 Fine-Tune

The local adapter was fine-tuned on the full ayjays132/PhillMagine320 dataset: 288 train rows plus 32 test rows. Conditioning includes every dataset feature: prompt, label, has_text_elements, source, and split.

python ImageGen\finetune_phillmagine320.py --epochs 1 --batch-size 2 --grad-accum 2 --image-size 128 --max-length 128 --lr 2e-5

The trainer uses CUDA with bf16 autocast, freezes the SDXL VAE, conditions from the local Phill-AXIOM embed_tokens table in model.safetensors, preserves the adapter checkpoint key set, and refreshes models/qwen_aligned_refiner/deep_16.pt from the saved adapter. The pre-finetune checkpoint is kept as adapter_model.pre_phillmagine320.pt.

Compatibility Contract

The pipeline keeps the existing adapter checkpoint intact. Architecture changes should be made in config.json only when retraining or intentionally migrating weights.