ltx-2.3-22b/distilled/video-to-video/lora

Generate video with audio from videos using LTX-2.3 Distilled and custom LoRA

ltx-2-19b/distilled/extend-video/lora

Extend videos with audio using LTX-2 Distilled and custom LoRA

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Apply dodge and burn effects with multiple modes and adjustable intensity.

ltx23-trainer-v2/extend-prefix

Train a LoRA that continues a video forward in time — supply an opening clip at inference and the model generates what comes next.

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

ltx23-trainer-v2/v2v

Train a LoRA that learns a video-to-video transformation from paired before/after clips, steered at inference by a reference (control) video.

Erase and replace any moment in your audio with AI-driven precision.

ltx23-trainer-v2/inpaint

Train a LoRA that regenerates a masked region of a video while keeping the rest unchanged, blending the new content with its surroundings.

bria/fibo-edit/edit/structured_instruction

Structured Instructions Generation endpoint for Fibo Edit, Bria's newest editing model.

InfinityStar’s unified 8B spacetime autoregressive engine to turn any text prompt into crisp 720p videos - 10× faster than diffusion models.

ltx23-trainer-v2/ic-lora/av2av-masked

Train an IC-LoRA that regenerates a masked video region (guided by kept pixels and a video reference) while jointly generating audio from an audio reference.

wan-trainer/i2v-720p

Train custom LoRAs for Wan-2.1 I2V 720P

Maya1 is a state-of-the-art speech model by Maya Research for expressive voice generation, built to capture real human emotion and precise voice design.

PersonaPlex is a real-time, full-duplex speech-to-speech conversational model that enables persona control through text-based role prompts and audio-based voice conditioning.

Add a darkening vignette effect around the edges of the image with adjustable strength

bria/fibo-lite/generate/structured_prompt/lite

Structured Prompt Generation endpoint for Fibo-Lite, Bria's SOTA Open source model

Lucy-5B is a model that can create 5-second I2V videos in under 5 seconds, achieving >1x RTF end-to-end

Diffusion based high quality edge detection

Fooocus extreme speed mode as a standalone app.

flux-krea-lora/stream

Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.

flux-lora/stream

Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.

Hyper-charge SDXL's performance and creativity.

Hyper-charge SDXL's performance and creativity.

Hyper-charge SDXL's performance and creativity.

ideogram/custom-models

Train Ideogram on your photos, your style, your subject, your look, from a small set of reference images to images that feel consistently yours

ltx2-v2v-trainer

Train LTX-2 for video transformation or video-conditioned generation.