Running on Zero
Agents
Cross-Modal Latent Fusion Playground
ðŸŽ
Dual-encoder sketch+RGB latent fusion (MSc, Surrey 2024)
Priyanka Kamila
pynk17
AI & ML interests
Generative Models, Diffusion & Flow Matching, Multimodal Learning, Computer Vision, Vision Transformers, Image & Video Generation, 3D Vision, Representation Learning, Model Evaluation, Efficient Inference
Recent Activity
updated a model 4 days ago
pynk17/pk_fewshot-aur-model published a model 7 days ago
pynk17/pkbloom-7b1-lora updated a model 7 days ago
pynk17/pkbloom-7b1-loraOrganizations
models 7
pynk17/pk_fewshot-aur-model
Unconditional Image Generation • 0.2B • Updated • 24
pynk17/pkbloom-7b1-lora
Text Generation • Updated
pynk17/sd-naruto-fp16-grad-checkpointing
Text-to-Image • 0.9B • Updated • 18
pynk17/sd-naruto-fp16
Text-to-Image • 0.9B • Updated • 14
pynk17/sd-naruto-fp32-baseline
Text-to-Image • 0.9B • Updated • 16
pynk17/my-small_diff-model
Text-to-Image • 0.1B • Updated • 42
pynk17/distilgpt2-finetuned-toxicity
Text Generation • 81.9M • Updated • 14
datasets 0
None public yet